Skip to main content
Glama

Search a creator's videos

search_creator_videos
Read-onlyIdempotent

Search everything one creator said across their transcribed videos, by meaning and in any language. Returns up to 5 distinct videos, each with its best moment, the exact quote, a timestamp and a link that opens the video at that second. The user does not need these videos in their own library. The creator is given by name, handle or slug, as listed by show_creators. When candidates is empty, read reason before answering: creator_unknown means SavedThat does not carry that creator at all, so say exactly that and offer the libraries in available_creators rather than claiming the creator never discussed the topic; creator_ambiguous means the name matched several, listed in did_you_mean; no_match means this creator genuinely does not cover it across searched_videos transcribed videos; search_unavailable and search_failed are our own trouble, so say the search is temporarily down and offer to retry.

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": {
      "creator": "<creator>",
      "query": "<query>"
    },
    "name": "search_creator_videos"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryYesThe question or topic to look for.
creatorYesCreator name, @handle or slug, e.g. "Alex Hormozi".

Output Schema

NameRequiredDescriptionDefault
queryYes
reasonNoPresent only when candidates is empty: WHY it is empty. creator_unknown means SavedThat has no such creator library (not that the creator is silent on the topic); no_match means the creator is here but does not cover the query.
creatorNo
candidatesYes
did_you_meanNoWith reason creator_ambiguous: the creators the reference matched.
searched_videosNoWith reason no_match: how many of the creator's transcribed videos were searched.
available_creatorsNoWith reason creator_unknown: the creator libraries SavedThat does carry, to offer instead.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Beyond the read-only annotations, the description discloses return structure, best-moment quoting, timestamps, links, and detailed error-state meanings. Its one weakness is saying it returns “up to 5” videos even though the schema allows the limit parameter to go to 8, so the disclosed cap is only accurate for the default. Apart from that, the behavioral context is strong.

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?

The description is front-loaded with purpose and return behavior, and the lengthy error-reason guidance is justified because it prevents wrong user-facing answers. It is still a dense paragraph, and the inaccurate “up to 5” phrasing could be tightened to reference the limit parameter. Overall it is informative rather than padded.

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 and read-only annotations already present, the description nevertheless covers the important return shape and the full empty-result taxonomy. Its main gap is the relationship between the limit parameter and the stated return cap, which is both unmentioned and slightly inaccurate. Otherwise it gives an agent enough context to call the tool and interpret failures 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?

The description adds real meaning beyond the schema for query (“by meaning and in any language”) and creator (“name, handle or slug, as listed by show_creators”). However, it never explains the limit parameter, and its “up to 5” statement can mislead callers who set limit above the default. The schema already documents limit structurally, but the description does not fully compensate.

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 states a specific verb and resource: semantic search across one creator's transcribed videos in any language. It also distinguishes the scope from the user's own library and ties creator identification to show_creators. An agent can tell this apart from search_my_library and the moment-lookup siblings.

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?

It explicitly says the creator is given by name, handle or slug as listed by show_creators, and that the videos need not be in the user's library. It also gives concrete guidance for every empty-candidates reason, including what to say to the user and when to offer available_creators or a retry. This is unusually complete when-to-use and fallback guidance.

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.