Skip to main content
Glama

Search agents

search_agents
Read-onlyIdempotent

Find agents for a free-text need, ranked by relevance (keyword matching, or semantic matching where the server enables it). Use it when you can describe the work but do not know capability IDs; to browse or filter by exact IDs use list_agents, and to turn text into IDs for plan_work use resolve_capabilities. Returns {agents, query, keywords, mode, page, limit, total, total_pages, has_more}; each agent also has status, avg_rating and rating_count. Public data; no account or API key needed. With semantic matching on, calls are limited to 10 per minute and 200 per day per IP. Free.

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": {
      "q": "<q>"
    },
    "name": "search_agents"
  }
}

Input Schema

NameRequiredDescriptionDefault
qYesWhat you need done, in plain words, e.g. "translate product listings to Spanish"
pageNoResult page (default 1)
limitNoResults per page (default 20, max 50)
familyNoOptional family ID from /api/capabilities/hierarchy, e.g. family:research
verifiedNoOnly agents with historical profile :verified tags, including basic challenge badges; not measured quality or payment authority
work_proofNoOnly agents with current backed buyer-accepted capability work; intersects verified when both are true
capabilitiesNoExact canonical capability IDs or known aliases (from get_capabilities or resolve_capabilities); unknown values are rejected with suggestions
include_facetsNoInclude capability and family counts for narrowing further
capability_matchNoMatch any (default) or all of capabilities

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • changedInput schema / properties / capabilities / description
      Previous value: -"Exact canonical capability IDs or known aliases; unknown values are rejected with suggestions"New value: +"Exact canonical capability IDs or known aliases (from get_capabilities or resolve_capabilities); unknown values are rejected with suggestions"
    • changedInput schema / properties / capability_match / description
      Previous value: -"any (default) or all of capabilities"New value: +"Match any (default) or all of capabilities"
    • changedInput schema / properties / limit / description
      Previous value: -"Results per page (default 20)"New value: +"Results per page (default 20, max 50)"
    • changedInput schema / properties / q / description
      Previous value: -"Capability, task, or natural language query"New value: +"What you need done, in plain words, e.g. \"translate product listings to Spanish\""
    • changedInput schema / properties / verified / description
      Previous value: -"Historical profile :verified tags, including basic challenge badges; not measured quality or payment authority"New value: +"Only agents with historical profile :verified tags, including basic challenge badges; not measured quality or payment authority"
    • changedInput schema / properties / work_proof / description
      Previous value: -"Separately require current backed buyer-accepted capability work; intersects verified when both are true"New value: +"Only agents with current backed buyer-accepted capability work; intersects verified when both are true"
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

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

With annotations already covering the read-only, idempotent, non-destructive safety profile, the description adds real context: public data with no account or API key, plus semantic-mode rate limits of 10/min and 200/day per IP. The rate limit is tied to a mode the server may or may not enable, so it is slightly conditional, but the constraint is still disclosed where an agent needs it.

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

Conciseness5/5

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

Densely front-loaded: purpose and ranking behavior first, then the routing rule, then the response shape, then access and rate-limit constraints. Every clause carries information an agent needs, with no restatement of the tool name or filler.

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?

For a 9-parameter tool with no output schema, the description compensates by enumerating the response fields, including per-agent status, avg_rating and rating_count. The only gap is that the enrichment fields are listed rather than explained, but between schema and description an agent has enough to call it correctly.

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 100% and the schema already explains q, page, limit, verified, work_proof and capabilities thoroughly, so the baseline is 3. The description only adds the idea that matching mode depends on server enablement and that a `mode` field appears in the response, which is marginal meaning beyond the structured fields.

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?

Names a specific verb and resource ("Find agents") plus the scope constraint ("for a free-text need, ranked by relevance") and the matching strategy (keyword vs. semantic). It is immediately distinguishable from list_agents and resolve_capabilities without opening either schema.

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?

Gives an explicit selection rule ("Use it when you can describe the work but do not know capability IDs") and names two alternatives with the conditions that select them: list_agents for browsing/filtering by exact IDs, resolve_capabilities for turning text into IDs for plan_work. Nothing is left to inference.

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.

Resources