Ontario Protocol

Find a task-matched x402 tool

find_x402_tool

Read-onlyIdempotent

Free buyer-side search across Ontario's fresh strict-ready paid profiles, Agentic Market, and Coinbase CDP Bazaar. Returns unverified marketplace candidates ranked by task relevance plus bounded source-reported recent activity, with optional Base/USDC budget filtering; nothing is probed, so listings may be dead or mispriced. ontario_find-api returns live-checked candidates. Paid Ontario publication adds no ranking score. Provider-side publication queries return the free listing validator and the 0.50 USDC publication workflow.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "find_x402_tool"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Maximum number of task-matched candidates to return, from 1 to 10.
`query`	Yes	Public task text only; never include credentials or private customer data.
`network`	No	Optional network filter, for example eip155:8453 or base.
`max_usdc`	No	Optional hard USDC price ceiling for returned candidates.
`active_only`	No	When true, require recent source-reported activity or fresh strict-ready Ontario profile evidence.

Output Schema

Name	Required	Description
`count`	Yes
`query`	Yes
`intent`	No	provider_publication when provider-side listing intent is routed to the listing validation and publication workflow.
`schema`	Yes
`candidates`	Yes
`provider_path`	No	Machine-actionable free validation, optional pending submission, and gated paid publication sequence.
`trust_boundary`	Yes
`candidate_status`	No
`selection_method`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 25, 2026

removedOutput schema / properties / agent_next_step
```
Removed value: -{
-  "type": "string"
-}
```
addedOutput schema / properties / candidate_status
```
Added value: +{
+  "type": "string"
+}
```

changedOutput schema / properties / intent / description

Previous value: -"provider_publication when provider-side listing intent is routed to the free-first publication workflow."New value: +"provider_publication when provider-side listing intent is routed to the listing validation and publication workflow."

First observedSep 5, 2026

TDQS

A4.5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations (readOnly/openWorld/idempotent) by disclosing that nothing is probed, that listings may be dead or mispriced, that activity is bounded and source-reported, and that paid publication confers no ranking advantage. These are exactly the expectations an agent needs before trusting results, and they are not derivable from structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and scope are front-loaded in the first clause, and the caveats and alternative routing follow logically. The closing sentence on provider-side publication queries is dense and somewhat opaque—mixing a validator pointer with a 0.50 USDC pricing note—which slightly blunts an otherwise tight description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With annotations and an output schema present, the description needn't explain return shape, and it covers sources, ranking policy, freshness limits, budget filtering, and one key alternative. The remaining gap is in a crowded sibling set of 18 tools where more than one alternative is named for disambiguation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description adds real meaning by framing max_usdc as an optional budget ceiling, network as Base-oriented filtering, and clarifying that active_only depends on source-reported or fresh-profile evidence. It does not add syntax-level detail for network identifiers, but the schema already carries examples.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('free buyer-side search' for x402 tools) and enumerates the exact sources searched (Ontario strict-ready profiles, Agentic Market, Coinbase CDP Bazaar). It also describes the return contract ('unverified marketplace candidates ranked by task relevance'), which lets an agent distinguish it from retrieval-style siblings without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly names the alternative for live-verified results: 'ontario_find-api returns live-checked candidates,' giving a clear selection condition. It also signals the buyer-side vs provider-side split in the final sentence. It stops short of routing against other overlapping siblings such as ontario_task_fit, agent_can_pay, or bazaar_buyer_intent_gap, so it is clear but not exhaustive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Ontario Protocol tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.