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

Annotations only declare readOnlyHint=false and destructiveHint=false, so the description carries the real burden and does well: it discloses cost ('uses no credits'), latency ('reads up to 19 frames and takes a few seconds'), state lifetime ('Proposals last a day'), that a numbered sheet is produced, and precisely what each proposal contains. The only gap is that it never explains why the call is a non-readOnly mutation beyond the ephemeral proposals.

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 purpose and the sibling routing before the dense return-value sentence. The middle sentence listing every proposal field is a long run-on chain that takes effort to parse, and the fully-null example call is only mildly useful, but nothing is truly wasted.

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?

No output schema exists, and the description fully compensates by enumerating the return contents (id, four corners in source/film/film_norm, width-to-height, outline quality, trackability, tracker range and lost stretches, numbered sheet). Combined with cost, timing and proposal lifetime, an agent has everything needed to call it and interpret the result.

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 coverage is 100%, so the baseline is 3, but the description adds meaning the schema does not: query drives the find_objects-box search path versus default flat-shape selection, and the seed frame / start-end range govern what gets proposed versus tracked. It also restates defaults (max 5, 1-10) that are already in the schema, so it is additive rather than fully compensating.

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 concrete verb and resource ('find flat surfaces... a sign, a screen, a poster, a wall') in a video or image, and separates itself from siblings by saying the surface is looked for inside boxes that find_objects draws and that the picked one is followed by track_plane. An agent can distinguish it from find_objects, track_plane and track_occluders 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.

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

Gives explicit routing: with a query the search is constrained to find_objects boxes, without one the best outlined flat shapes win; occluding content is explicitly deferred to track_occluders, and following the chosen proposal is deferred to track_plane with fromProposal. When to pass a query and when to leave it null is spelled out with examples.

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