Bake local video rotation into pixels

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

Goes well beyond the annotations: it warns that color and precision can change (a real quality-loss caveat), states that all generated frames and timing are verified, notes exact AAC copy when requested, and discloses the local browser plus native H.264 requirement. That is exactly the extra context annotations can't carry.

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

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

Four dense sentences, front-loaded with the operation and its output format before the caveats. No filler, though the mixing of output format, verification, and prerequisites in one block makes it slightly list-like.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

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

For a re-encoding mutation with no output schema and no annotations carrying behavior, the description covers what gets produced, what may degrade, and what environment is needed. The only real gap is max_side, which affects output resolution but is never explained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With only 40% schema coverage, the description does real work: it enumerates the 90/180/270 options and clarifies the turn applies on top of source orientation, and the AAC copy statement maps to keep_audio. It says nothing about max_side, which remains undocumented in both schema and description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — decode H.264, permanently rotate pixels, emit a new MP4 with an identity display matrix — which is far more precise than the name 'bake' on its own. It implicitly separates itself from a metadata-only rotate, but never names abox_video_rotate, so sibling differentiation is left to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The words 'permanently' and 'newly encoded' hint that this is the re-encode path rather than the metadata path, and the local-browser/H.264 prerequisite gives some context. But there is no explicit 'use this instead of abox_video_rotate when...' statement, so an agent picking between the two must reason it out.

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