AgentTools
Split text into retrieval-friendly chunks with a token budget and sentence-aware boundaries. Overlap between consecutive chunks preserves context across splits — the standard preparation step before embedding. Use this when an agent needs to rAG-ready chunks with token budgets and overlap.
The wallet the 402 directs payment to. Its whole payment record — every payer, every chain — is on the merchant page.
Asset 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913
The payTo wallet does not resolve to a registered ERC-8004 agent. That is not a verdict on the service — most of the catalog is unregistered.
Accepts
The payment requirements as published to the catalog. Read the live 402 before paying — a price here is a claim, not a quote.
Pay 0.005 USDC on Base to 0x8a0F…2b0f6. The signed payment is good for 5 minutes.
- Paid to
- 0x8a0F…2b0f6
- USD Coin contract
- 0x8335…02913
- Payment window
- 5 minutes
- As published
- 5000 smallest units
The catalog’s raw entry
[
{
"asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
"extra": {
"name": "USD Coin",
"version": "2"
},
"payTo": "0x8a0F2b0a6C82D1c54B16E2e4DEcd18fF0802b0f6",
"amount": "5000",
"scheme": "exact",
"network": "eip155:8453",
"maxTimeoutSeconds": 300
}
]Extensions
{
"bazaar": {
"info": {
"input": {
"type": "http",
"method": "GET",
"queryParams": {
"text": "Retrieval-augmented generation improves factuality. First, documents are split into chunks. Second, chunks are embedded into vectors. Third, the agent retrieves the top matches for a query. Overlap keeps ideas that straddle boundaries intact. Finally, the model answers with citations.",
"targetTokens": 60,
"overlapTokens": 15
}
},
"output": {
"type": "json",
"example": {
"tool": "text-chunker",
"result": {
"steps": [
"Split into 6 sentence units",
"Pack units up to 60 estimated tokens",
"Carry ≈15 tokens of overlap between consecutive chunks"
],
"table": {
"rows": [
[
0,
55,
"Retrieval-augmented generation improves factuality. First, d…"
],
[
1,
22,
"Overlap keeps ideas that straddle boundaries intact. Finally…"
]
],
"columns": [
"Chunk",
"Est. tokens",
"Preview"
]
},
"value": 2,
"answer": "2 chunks",
"details": [
{
"label": "Input (chars / est. tokens)",
"value": "285 / ≈65"
},
{
"label": "Avg chunk size",
"value": "≈39 tokens"
},
{
"label": "Boundary strategy",
"value": "paragraph → sentence → word"
}
],
"artifacts": {
"chunks": "[{\"index\":0,\"estTokens\":55,\"text\":\"Retrieval-augmented generation improves factuality. First, documents are split into chunks. Second, chunks are embedded into vectors. Third, the agent retrieves the top matches for a query. Overlap keeps ideas that straddle boundaries intact.\"},{\"index\":1,\"estTokens\":22,\"text\":\"Overlap keeps ideas that straddle boundaries intact. Finally, the model answers with citations.\"}]"
},
"answerLabel": "≈65 tokens → chunks of ≤60 tokens, overlap 15"
}
}
}
},
"schema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"input"
],
"properties": {
"input": {
"type": "object",
"required": [
"type",
"method"
],
"properties": {
"type": {
"type": "string",
"const": "http"
},
"method": {
"enum": [
"GET"
],
"type": "string"
},
"queryParams": {
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"description": "Text"
},
"targetTokens": {
"type": "number",
"description": "Target tokens per chunk"
},
"overlapTokens": {
"type": "number",
"description": "Overlap tokens"
}
}
}
},
"additionalProperties": false
},
"output": {
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"type": "string"
},
"example": {
"type": "object"
}
}
}
}
}
},
"analytics": {}
}Provenance
- Seen in the source catalog
- 2026-10-11 01:06Z
- Last indexed by Roundhouse
- 2026-10-12 13:10Z
- Last enriched (probe, favicon, geo)
- 2026-10-02 01:15Z
- x402 version
- 2
- Max timeout
- 300s
- Liveness probe
- HTTP 402
Hand this page to an agent
Copy the prompt and paste it into Claude, an MCP client or your own agent — it will vet this service and call it over the free read API. No key, no account.
GET api.roundhouseai.io/v0/endpoints
This endpoint's own trailing-30-day call count, as published by the upstream catalog and snapshotted daily. 15 snapshots so far. Verified volume counts only settlements with an on-chain EIP-3009 marker.
Show the promptHide the prompt
Using Roundhouse, look up the x402 service AgentTools and tell me whether it is worth paying: what a call costs, whether the endpoint answered when last probed, and what its payment record actually shows. curl -s 'https://api.roundhouseai.io/v0/endpoints?q=AgentTools' curl -s 'https://api.roundhouseai.io/v0/merchants/<the payTo wallet returned above>' Then call it: read the price from the live 402 at https://agenttools-hub.vercel.app/api/v1/dev/text-chunker, never from a cached figure, and pay with an x402 client. The /v0 API needs an API key (`authorization: Bearer rh_live_…`) on everything except /v0/unified* and /v0/endpoints. Either pay over x402 (mint a personal key for $0.01 at GET https://api.roundhouseai.io/v0/test/x402), or ask me for an organization key, which I create at https://roundhouseai.io/dashboard/connections. If you have neither, ask before going further. If you do not have Roundhouse tools or skills installed, read https://roundhouseai.io/skill.md first — it is the whole procedure.