Skip to main content
Glama

Search every transcript

search_transcripts
Read-only

Full-text search across transcripts: matching episodes with snippets, newest relevance first, 20 a page. Optional speaker person slug, podcast/topic slugs, publication year and UTC dates (YYYY-MM-DD). Speaker mode requires literal words/quoted phrases in one qualified passage and reports indexed coverage and playback windows. Needs an API key; billed per search (see list_services).

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_transcripts"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNo
yearNoUTC publication year, intersected with the explicit date range.
queryYes
topicNoCanonical slug from find_topics; explicit empty matches nothing.
date_toNo
podcastNoA slug from find_podcasts.
speakerNoCanonical person slug. Matches words in qualified speaker passages only; partial indexed coverage.
date_fromNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / speaker
      Added value: +{
      +  "description": "Canonical person slug. Matches words in qualified speaker passages only; partial indexed coverage.",
      +  "maxLength": 200,
      +  "type": "string"
      +}
    • addedInput schema / properties / topic
      Added value: +{
      +  "description": "Canonical slug from find_topics; explicit empty matches nothing.",
      +  "maxLength": 200,
      +  "type": "string"
      +}
    • addedInput schema / properties / year
      Added value: +{
      +  "description": "UTC publication year, intersected with the explicit date range.",
      +  "maximum": 9998,
      +  "minimum": 1000,
      +  "type": "integer"
      +}
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Beyond the readOnly/openWorld annotations it discloses ranking ("newest relevance first"), page size, a per-search billing cost, and that speaker mode reports indexed coverage and playback windows - meaningful behavior an agent can't get from structured fields.

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?

One dense but front-loaded paragraph: what it returns first, then filters, then speaker-mode caveat, then cost. Every clause carries information, though the packed phrasing slightly hurts scannability.

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 an 8-parameter, no-output-schema search tool it covers result shape, pagination, ranking, speaker-mode limitations and cost. Missing only edge behavior such as empty results or how snippets are truncated.

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?

At 50% schema coverage the description compensates for the undocumented parameters by naming the speaker slug, podcast/topic slugs, year and UTC dates with a YYYY-MM-DD format hint. It still leaves page bounds and query length to the schema, so it only partly closes the gap.

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?

States a specific verb and resource ("Full-text search across transcripts") plus the shape of the result ("matching episodes with snippets"), which separates it cleanly from get_transcript and the analysis tools.

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?

Gives useful preconditions (API key required, billed per search, "see list_services") and explains when speaker mode is valid, but never says when to prefer this over get_transcript or ask_question.

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