Skip to main content
Glama

Review a shot

review_shot
Read-only

A strict second look at a generated still or clip before you spend more on it: whether it matches the brief, where people are looking, whether a device screen can really be seen, hands and faces, stray text, and anything physically odd. Returns pass or fail per check and a prompt fix. Run it on every still before animate_image, and on every clip before render_video. 5 credits.

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": "review_shot"
  }
}

Input Schema

NameRequiredDescriptionDefault
briefNoWhat the shot should show, in plain words. Defaults to the job's prompt.
imageNoOr a still: stored path or public https
videoNoOr a clip: stored path or public https (start, middle and end frames are checked)
job_tokenNoA finished image or video job_token
green_screenNoThe device screen is meant to be plain green (generated with green_screen)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, and nothing here contradicts them. The description adds real context beyond the annotations: the strictness stance, the cost ('5 credits'), and the output shape ('pass or fail per check and a prompt fix'). It stops short of stating latency or that exactly one of job_token/image/video must be supplied.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded, the check list is dense but each item is informative, and the workflow rule and cost land in the final sentence. No filler or repetition of the title.

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 no output schema, the description correctly compensates by describing the return value (pass/fail per check plus a prompt fix) and discloses cost. The one gap is that with zero required parameters it never says that one input source (job_token, image or video) must be chosen, which is the main calling pitfall.

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 description coverage is 100%, so the schema already explains brief, image, video, job_token and green_screen. The description only indirectly gestures at parameters ('matches the brief', 'whether a device screen can really be seen'), adding little syntax or precedence detail beyond the structured fields, so the baseline 3 applies.

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 names a specific verb ('strict second look') and resource ('a generated still or clip') and enumerates exactly what is checked: brief match, gaze, device-screen visibility, hands/faces, stray text, physical plausibility. That enumeration makes it unmistakable versus siblings like review_render or get_render.

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 placement in the workflow: run on every still before animate_image and on every clip before render_video. That is a concrete when-to-use rule with named downstream alternatives, leaving little to inference.

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