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

Annotations cover the safety profile (idempotent, non-destructive, closed-world), and the description adds substantial context beyond them: the call is project-scoped and returns project identity, focus_track REPLACES the complete per-shot track rather than appending, tracks survive trims and speed changes, and the HD canvas note flags the limit of what this recovers. That is exactly the kind of non-obvious behavior an agent cannot infer from structured fields.

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?

Front-loaded with the project-scope constraint and the core action, and every sentence carries a distinct fact (defaults, coordinates, replacement semantics, the HD-canvas caveat). It is dense — the focus_track and canvas sentences could be tightened — but nothing is padding.

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 6-param mutation tool with no output schema and thin schema descriptions, the definition covers scope, return identity, enum meanings, default behavior, track replacement semantics, and the alternative tool. Nothing an agent needs to call it correctly is missing.

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?

Schema description coverage is only 17%, so the description must compensate, and it does: it enumerates ratio and mode values with the default ('crop (default)'), defines the coordinate system for focus_x/focus_y ('(0,0) = top-left', fractions of the source frame), and specifies the focus_track item shape and that t0/t1 are in SOURCE seconds. This meaningfully exceeds what the schema conveys.

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+resource ('Set the output aspect ratio for every render') and scopes it to every render, which is exactly what distinguishes it from the zoom/reframe siblings. It also names auto_reframe explicitly as the different tool for the same user goal, so an agent can route without opening either schema.

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?

Gives explicit routing advice ('For make it 9:16 on real footage PREFER auto_reframe') plus a required workflow step ('Read get_edl(frame) first; change only the desired spans'). It also states a precondition for focus_x/focus_y (omitting them yields a dead-center crop) that tells the agent when to supply them.

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