Skip to main content
Glama

Search transcripts

search
Read-onlyIdempotent

Semantic + keyword search across transcripts of 158 continuously-updated YouTube/podcast channels (interviews, tech, business, science, health, politics) and the user's own ingested library. Returns the most relevant passages with timestamps and deep links. Use this first for "what has X said about Y" questions; then call get_passage for more context around a hit, or get_transcript for the full text. Call list_channels to see which channels are indexed. For a summary or key points of one specific YouTube video, call show_player first with a short summary and the key points as moments, then write your answer citing timestamps.

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"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryYesNatural-language question or keywords
scopeNopublic = indexed channels; library = media this user ingestedall
channelsNoRestrict to channels by name, handle or alias (e.g. "Lex Fridman", "@hubermanlab", "JRE")
item_idsNoRestrict to specific items (ids from earlier results)
published_afterNoYYYY-MM-DD, inclusive
published_beforeNoYYYY-MM-DD, inclusive

Output Schema

NameRequiredDescriptionDefault
queryYes
resultsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful beyond-schema context: the index is continuously updated, it spans both public channels and the user's private library, and results come back as excerpts with timestamps and deep links. It stops short of disclosing ranking behavior, result caps, or empty-result handling.

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?

Front-loaded with capability and corpus scope, then returns, then routing — a sensible ordering with little filler. The final sentence about show_player is the weakest part: it is longer than needed and describes another tool's workflow rather than this one's.

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?

With an output schema present and rich annotations, the description need not explain return values, and it already covers corpus scope, defaults implied by "use this first", and the follow-up tool chain. Remaining gaps are minor: no mention of the limit cap, ranking/pagination behavior, or what an empty result set implies.

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 86%, so the schema already explains query, scope, channels, item_ids and date bounds. The description adds only indirect meaning ("the user's own ingested library" gestures at the scope enum) and never mentions limit, channel aliases, or date filtering. Baseline 3 is appropriate when the schema carries this much detail.

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 concrete verb and resource ("Semantic + keyword search across transcripts") plus the exact corpus (158 continuously-updated YouTube/podcast channels and the user's ingested library) and the return shape (relevant passages with timestamps and deep links). This is distinguishable from siblings like get_transcript or get_passage without opening any schema.

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 explicit routing: "Use this first for 'what has X said about Y' questions", then get_passage for surrounding context, get_transcript for full text, list_channels to see the index. The closing sentence about calling show_player for single-video summaries is tangential and somewhat confusing as search guidance, but the primary when-to-use/when-to-use-something-else instructions are clear.

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