Skip to main content
Glama

search_tools

Read-onlyIdempotent

Call this FIRST when you need a tool, API, SDK, CLI or MCP server for a task you can't do yet: describe the task in plain words (job) and get one best_pick with a paste-ready use_it snippet (MCP client config JSON, install command, or API base URL + docs). One call is usually enough: best_pick.summary says in one line what to use and why (reasons: vendor-official or third-party, live check, auth, read-only or can send/spend, outcome reports), best_pick.report_call is the one-line report to send after you use it; results lists ranked alternatives with score breakdowns (evidence, source URL, date), side effects and human steps; verdict is honest (good_match / weak_matches / nothing_good_found / cannot_work_as_asked / not_a_tool_job, then best_pick is null and answer says why; not_a_tool_job adds a curated workaround). Constraints written in the job ('no account', 'nothing paid', 'no new token scopes', 'headless') or in constraints are checked per result (constraint_check). Free, no key. Returns a top-level report_token for optional feedback.

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": {
      "job": "<job>"
    },
    "name": "search_tools"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobYesThe task in plain words, e.g. 'send SMS to customers', 'read my Google Calendar', 'GitHub MCP server'
stageNooptional, self-declared
clientNooptional, e.g. claude-code, cursor, my-agent
detailNobrief drops per-result score_breakdown and why[] (about 4x smaller); default full
agent_typeNooptional, self-declared
constraintsNo
watcher_keyNooptional: get an alert if nothing good is found now but a match appears later

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • addedInput schema / properties / constraints / properties / headless
      Added value: +{
      +  "type": "boolean"
      +}
    • addedInput schema / properties / constraints / properties / no_account
      Added value: +{
      +  "type": "boolean"
      +}
    • addedInput schema / properties / constraints / properties / no_admin
      Added value: +{
      +  "description": "no admin install or third-party approval",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / constraints / properties / no_new_key
      Added value: +{
      +  "description": "no new API key, token or scopes",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / constraints / properties / no_paid
      Added value: +{
      +  "type": "boolean"
      +}
    • addedInput schema / properties / constraints / properties / require
      Added value: +{
      +  "description": "same constraints as a list, e.g. [\"no_account\",\"no_paid\"]; constraints written in the job text are also read",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / constraints / properties / self_hosted
      Added value: +{
      +  "type": "boolean"
      +}
    • addedInput schema / properties / constraints / properties / server_side
      Added value: +{
      +  "type": "boolean"
      +}
  2. Changed1 schema field changed
    • addedInput schema / properties / detail
      Added value: +{
      +  "description": "brief drops per-result score_breakdown and why[] (about 4x smaller); default full",
      +  "enum": [
      +    "full",
      +    "brief"
      +  ],
      +  "type": "string"
      +}
  3. Changed1 schema field changed
    • addedInput schema / properties / constraints / properties / healthy_only / description
      Added value: +"only entries whose latest check passed: MCP handshake ok or auth_required, or (HTTP APIs) base URL reachable"
  4. Changed1 schema field changed
    • changedInput schema / properties / job / description
      Previous value: -"What you need to get done, e.g. 'send SMS to customers'"New value: +"The task in plain words, e.g. 'send SMS to customers', 'read my Google Calendar', 'GitHub MCP server'"
  5. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnlyHint, idempotent, non-destructive, closed-world), and the description adds substantial context beyond them: 'Free, no key', the returned report_token, the full verdict taxonomy including best_pick=null cases, and how constraints in the job text are checked per result. It also discloses output size behavior via the brief/full detail distinction.

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

Conciseness3/5

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

The critical instruction is correctly front-loaded ('Call this FIRST'), but the rest is a dense wall of colon-and-parenthesis clauses covering return shape, verdicts, constraints, and feedback tokens in one block. Every element is informative, yet the packing makes it 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?

For a 7-parameter tool with a nested constraints object and no output schema, the description compensates by fully describing the response envelope (best_pick, use_it, summary, report_call, results, verdict, report_token) and the failure modes. An agent has everything needed to call it once and interpret the result.

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 high (86%) so the schema carries most parameter documentation; the description still adds meaning the schema does not, notably that constraints written in the job string are parsed and checked (constraint_check) and what each verdict outcome implies. It does not mention watcher_key or client/stage, leaving those entirely to the schema.

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?

The description names a specific verb and resource ('when you need a tool, API, SDK, CLI or MCP server... describe the task in plain words and get one best_pick with a paste-ready use_it snippet'), which is far more specific than 'search'. It also implicitly separates itself from siblings by instructing 'Call this FIRST', so an agent knows this is the entry point rather than a follow-up call.

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?

There is an explicit trigger ('when you need a tool... for a task you can't do yet') and an explicit efficiency rule ('One call is usually enough'), plus guidance that report_call exists for post-use reporting. It stops short of naming the sibling tools (get_tool, report) as alternatives or stating when not to call it, so it falls just below the top band.

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