Skip to main content
Glama

Search browser skills

search_skills
Read-only

Same as find_skill: search verified, replayable browser skills for doing a task on a website or web app. Returns cid, site, site_kind (real or demo/mock), params, risk flags, verified run and replay counts and how_to_run. 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": "search_skills"
  }
}

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

A4/5.0
Behavior4/5

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

Annotations already cover read-only and open-world scope, but the description adds substantive context the annotations cannot: the exact return fields (cid, site, site_kind real vs demo/mock, params, risk flags, verified run and replay counts, how_to_run). It also discloses the endpoint capability boundary (no run_skill) and the allowlist gate on try_skill. It stops short of auth or rate-limit behaviour, which keeps it off a 5.

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?

Three sentences, front-loaded with the core operation, then return shape, then the routing caveat — good ordering with no filler. The opening "Same as find_skill" is slightly wasteful since it forces the agent to consult a sibling's definition instead of stating the scope directly.

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, so the enumerated return fields are exactly what an agent needs to judge whether results are usable. Combined with the run/replay verification context and the try_skill routing, nothing essential is missing for a 2-parameter read-only search.

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 description coverage is 100% — both query (with a worked example) and limit (default 3, effectively capped at 5, threshold filtering) are documented in-schema. The description adds no constraints, formats or defaults of its own, so the schema does all the work and baseline 3 applies.

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?

A specific verb and resource ("search verified, replayable browser skills") plus the object of the search ("for doing a task on a website or web app") make the purpose unambiguous. However, "Same as find_skill" asserts equivalence with a sibling rather than differentiating from it, so an agent still can't tell from this sentence why two tools with identical behaviour exist.

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?

Gives a clear exclusion and a named alternative: "This HTTP endpoint does not offer run_skill; allowlisted skills can be tried with try_skill." That is real when-to-use guidance. What's missing is any statement of when to prefer this over find_skill, since the description claims they are the same.

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.