Skip to main content
Glama

detect_people

Read-onlyIdempotent

Number visible faces in a source video asset in this Project and return a numbered contact sheet, absolute source appearance times, analysisId, videoId and range. Use exactly the 4–30 second range you will remake. Whole seconds from start are analysed, matching remake duration; never silently select a different range for the user. Before object-swapping a person, inspect this sheet, select every number belonging to that target, then pass peopleAnalysisId and plan.targets[].people to submit_video_remake. Numbers are local to this source and range, not global identities. One person can have several numbers; exclude false detections and other people. A hidden face has no number. Runs on ChatCut cloud machines, with no generation credits charged. Capacity and account limits still apply. If pending, wait about 30 seconds and call again with identical arguments to reuse the running task; do not resubmit a remake to poll analysis. If a visibly present target is missing from the sheet, do not invent numbers or silently drop requested identity or hair controls. Inspect a clearer range and report the detection gap before proposing another approach. Analysis expires; repeat it when the source or range changes or an expiry is reported. Head covering reduces source-face residue but does not guarantee every frame or review approval. Never reveal internal models, providers, versions, embeddings or raw errors to the user.

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": {
      "video": "<video>"
    },
    "name": "detect_people"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoEnd in seconds, default video end.
startNoStart in seconds, default 0.
videoYesSource video asset.
projectIdNoProject for this call (full ID or unambiguous prefix). Explicit-timeline calls never change the target of later calls; legacy project selection applies otherwise.
timelineIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds substantial traits they cannot express: cloud execution, no generation credits charged, account and capacity limits still apply, task reuse via identical arguments, and analysis expiry. It also clarifies the semantic nature of the output (numbers are local to source+range, not global identities) and a disclosure policy for internal errors. The only gap is it does not describe pagination or sheet layout.

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 a clear first sentence about what it does and what it returns, then moves into usage and failure handling. Most sentences target a concrete failure mode, but the policy tail ('Never reveal internal models, providers, versions, embeddings or raw errors') and repeated warnings about not inventing numbers or silently changing ranges could be tightened without losing meaning.

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?

No output schema exists, yet the description specifies the return surface (contact sheet, absolute source times, analysisId, videoId, range) and covers async polling, expiry, and the detection-gap case, which is unusually complete. The remaining gap is that timelineId stays unaddressed and the sheet's visual format is only implied.

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 80%, so the baseline is 3, but the description adds real meaning for start/end: the range must match the remake duration and whole seconds from start are what get analysed. It also anchors the video/range pair as the identity of an analysis. timelineId is left undocumented in both schema and description, which is why this is not a 5.

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 chain: 'Number visible faces in a source video asset in this Project and return a numbered contact sheet, absolute source appearance times, analysisId, videoId and range.' The output is enumerated, so an agent knows exactly what it gets and how it differs from siblings like submit_video_remake, which is named as the downstream consumer.

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?

Explicit about when to use it (before object-swapping a person, then pass peopleAnalysisId and plan.targets[].people to submit_video_remake), how to scope the call ('Use exactly the 4-30 second range you will remake'), and how to behave on pending (wait ~30s, call again with identical arguments, do not resubmit a remake). It also covers the failure path: inspect a clearer range and report the detection gap rather than inventing numbers.

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.