Skip to main content
Glama

media_look

Read-only

SEE the footage: decoded frames come back as an image you can look at. Give asset_id to look at one clip's source (times in source seconds), or leave it out to look at the timeline (times in timeline seconds; each frame is the top visible clip under the playhead). Pass times=[...] for exact moments, or start_s/end_s/count to sample a range (max 12). Several frames come back as one numbered contact sheet. Use it to check who is on camera, framing, a bad frame, which angle is which. Check already_noted first: if another agent wrote down what's there, you may not need to look. After looking, save what you learned with media_note. On a local project a timeline look is the FINISHED picture by default (as the preview shows it: zoom and position in the output frame, stacked tracks, transparency, Animate scenes; drawn by the desktop app; captions, shapes, grades and effects listed in words as not drawn). finished=false, a cloud project, or the desktop app being unavailable gives each clip's raw source frame instead, with a framing note saying which part of it the video shows. compare_revision=N also draws revision N of the timeline beside it (before | now).

response_detail (summary|ids|compact|full), fields (dotted paths), cursor (next page) — see the server instructions.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "media_look"
  }
}

Input Schema

NameRequiredDescriptionDefault
countNo
end_sNo
sheetNo
timesNo
cursorNo
fieldsNo
job_idNo
layersNo
start_sNo
asset_idNo
finishedNo
response_detailNo
compare_revisionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / layers
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "boolean"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Layers"
      +}
  2. Changed2 schema fields changed
    • addedInput schema / properties / compare_revision
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "integer"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Compare Revision"
      +}
    • addedInput schema / properties / finished
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "boolean"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Finished"
      +}
  3. Added

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description goes well beyond them: a max of 12 sampled frames, frames returned as one numbered contact sheet, local-project timeline looks defaulting to the FINISHED composite (with what is drawn vs only listed in words), and the finished=false / cloud / desktop-unavailable fallback to raw source frames plus a framing note. The remaining gap is operational rather than behavioral: nothing is said about latency, cost, or how large the returned image is.

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 core modes and the sampling options are front-loaded, and nearly every sentence carries non-obvious information (units differ by mode, 12-frame cap, contact sheet, finished-picture default). It is a single dense block with the local-vs-cloud rendering aside embedded mid-paragraph, which 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.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 13-parameter, description-less schema with no output schema, this definition explains the mode switch, units, sampling, the finished/raw behavior difference, and the compare-revision panel — enough to call it correctly in the common cases. The three unexplained parameters (sheet, layers, job_id) and the vague 'see the server instructions' tail are the only meaningful holes.

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 description coverage is 0%, so the description carries the full burden, and it explains most of the 13 parameters in prose: asset_id, times vs start_s/end_s/count (with units in source vs timeline seconds), finished, compare_revision (before | now), response_detail, fields, and cursor. sheet, layers, and job_id are never explained, so an agent must guess three parameters entirely, which keeps this below full marks.

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 first sentence states a concrete verb and resource: decoded frames come back as an image you can look at. It then splits the two modes precisely (asset_id = one clip's source, omitted = timeline top-visible-clip under the playhead), which is enough to distinguish this from screen_look or ws_read 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit use cases (who is on camera, framing, a bad frame, which angle is which), a prerequisite check (call already_noted first and skip the look if another agent already documented it), and a follow-up action (persist findings with media_note). The asset_id vs timeline split is itself a when-to-use rule, and it names the flags that change which picture you get.

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.