Agent Tested

Find tools for a task

find_tools_for_task

Read-onlyIdempotent

Describe what you need to do (e.g. 'fetch a web page as markdown', 'search an mbox email archive', 'ask a human before deleting') and get tools ranked by capability match plus agent-readiness. Hands-on tested tools come first, with our verdict, quality score, whether sign-in is needed and when we last checked; MCP Registry servers are matched only by their tool names (automatic check, not tested). Each result says why it matched and links to its page. Same as GET /api/find?task=.

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": {
      "task": "<task>"
    },
    "name": "find_tools_for_task"
  }
}

Input Schema

Name	Required	Description	Default
`kind`	No		all
`task`	Yes	What you need to do, in plain words
`limit`	No
`no_signin`	No	Only tools usable without sign-in

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 28, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds real value beyond that: tested tools rank first and carry a verdict, quality score, sign-in status and last-checked date, while registry entries are matched on name only and are untested. That provenance difference is exactly the trust signal an agent needs; only pagination/limit behavior is left unstated.

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?

Front-loaded with the action and concrete example inputs before the ranking/result detail, which is the right order. The result-field enumeration is a bit listy, but every clause conveys a filterable or trust-relevant attribute, so little is wasted.

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?

No output schema exists, and the description carries that burden competently by naming what each result contains (verdict, quality score, sign-in requirement, last-checked, match rationale, link). Combined with a working example and the API route, an agent could call this correctly; only `kind`/`limit` semantics are missing.

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

Parameters3/5

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

Schema coverage is 50% — `task` and `no_signin` are documented in the schema, `kind` and `limit` are not. The description partially compensates by explaining the tested-vs-registry distinction that `kind` controls, but never states the enum values or what `limit` bounds. Baseline 3 is appropriate.

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

Purpose4/5

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

States a specific verb and resource: describe a task, get tools ranked by capability match plus agent-readiness. The ranking inputs (tested verdicts, registry name-matching) make the capability unambiguous. It never names the sibling it overlaps with most (`search_tools` / `find_working_mcp_servers`), so it is clear on its own but not differentiated from siblings.

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

Usage Guidelines3/5

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

The three example tasks ('fetch a web page as markdown', 'search an mbox email archive', 'ask a human before deleting') imply the natural-language discovery use case well. There is no explicit when-not, no prerequisites, and no routing hint against `search_tools` or `find_working_mcp_servers`, so usage must be inferred.

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

All Agent Tested 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.

Resources

Need Help?