Skip to main content
Glama

Find a browser skill for a website task

find_skill
Read-only

Find a verified browser skill for a task on a website or web app (fill a form, file or look up a ticket, add to cart, export a report). Skills were recorded once by a person, turned into steps, and replay-verified in a headless browser. Returns up to 3 matches (limit: up to 5) above a confidence threshold, each with cid, name, site, site_kind (real site, or an Agentboard demo/mock site), params with examples, risk flags, steps that need human approval, how_to_run and a trust card computed from its signed runs; or matches: [] with a no-match message. check_workflow is the cheaper first call; neither runs anything. This HTTP endpoint does not offer run_skill; allowlisted skills can be tried with try_skill.

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_skill"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNomax results: default 3, up to 5 (larger values return at most 5); only matches above the confidence threshold are returned, so there may be fewer
queryYesthe task in plain words, e.g. "create a support ticket for dana@globex.com"

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / limit / description
      Previous value: -"max results (default 5)"New value: +"max results: default 3, up to 5 (larger values return at most 5); only matches above the confidence threshold are returned, so there may be fewer"
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the readOnlyHint/openWorldHint annotations: explains skills are human-recorded and replay-verified headlessly, that results are capped at 3 (limit up to 5) above a confidence threshold, that site_kind may be a mock/demo site, and that some steps require human approval. It also confirms the non-executing nature, consistent with readOnlyHint.

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 routing are front-loaded in the first clause and every sentence carries information, but the return-field enumeration (cid, name, site, site_kind, params, risk flags, steps, how_to_run, trust card) is a dense list in a single sentence that is harder to scan than it needs to be.

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

Completeness5/5

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

There is no output schema, and the description compensates by enumerating the return payload, including the empty-match case (`matches: []` with a no-match message). For a 2-param read-only search tool, nothing needed to call or interpret it is missing.

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 both params are already documented; the description nonetheless adds meaning by tying the limit to the confidence threshold and warning that fewer than the limit may come back. The query semantics are only illustrated by example, which duplicates the schema rather than extending it.

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?

Specific verb+resource ("Find a verified browser skill") with concrete task examples (fill a form, file a ticket, add to cart). It distinguishes itself from siblings by naming check_workflow and try_skill and by qualifying the resource as replay-verified recorded skills, not generic search.

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

Usage Guidelines5/5

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

Explicitly routes the agent: "check_workflow is the cheaper first call; neither runs anything," and states that run_skill is unavailable on this endpoint while try_skill covers allowlisted skills. When-to-use, when-to-use-something-cheaper, and when-not-available are all covered.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.