Skip to main content
Glama

auto_fix

Runs a self-check loop on a video: a vision model judges it, adjusts settings to fix drift, missing action, melting ends or hands, and re-renders up to 3 times, returning the best take.

Instructions

The self-check loop for one video: a vision model judges it, the settings are fixed by the kind of problem (drift = less movement, no action = more movement, end melts = shorter, hands/melting = avoid list) and it renders again, at most tries times (1-3). Every try is kept; the answer names the best one. problems: if you already looked (review_video), say what you saw so the first judge call is skipped: drift, wrong_subject, no_action, too_much_motion, hands, melting, end_melts, talking, blurry. Returns a fix id; job_status(fix id) follows it.

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": "auto_fix"
  }
}

Input Schema

NameRequiredDescriptionDefault
triesNo
videoYes
priorityNouser
problemsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior5/5

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

Beyond the annotations, the description discloses the iterative loop, the mapping from problem type to corrective setting changes, the 1-3 try cap, that every try is retained, and that the best result is named. This is substantive behavioral context for a mutating, non-readonly tool. The annotations already confirm non-destructive and closed-world behavior, and the description adds the internal decision logic.

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 around purpose and process, and each sentence adds operational detail (mapping, try cap, review shortcut, fix id follow-up). The parenthetical mapping is dense but useful rather than decorative; the one awkward line break does not obscure meaning. Minor tightening could improve readability, but there is little wasted text.

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 complex iterative tool with no output schema, it covers the main workflow, the try limit, problem values, and the returned fix id needed to continue with job_status. The missing priority semantics and lack of any detail about output beyond the fix id prevent full completeness, but an agent has enough to invoke and track the job.

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 0%, so the description must explain the four inputs. It explains tries (range 1-3) and problems (allowed values plus the effect of supplying them), but it says nothing about priority and only implicitly identifies video. That leaves meaningful parameter meaning missing despite the useful detail on problems.

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 opens with a specific scope ('self-check loop for one video') and explains the concrete mechanism (vision judge, settings correction, re-render), which is far more than a restatement of the name. It also differentiates from review_video by explaining how an existing review can be supplied to skip the first judge call. An agent can identify the tool's role without opening the 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?

It gives a clear conditional workflow: if the agent already used review_video, pass the observed problems so the first judge call is skipped, and use job_status with the returned fix id to follow progress. It does not explicitly say when to prefer auto_fix over other sibling tools or when not to use it, but the review_video and job_status handoffs provide actionable context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.