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

Annotations already declare readOnlyHint=false and destructiveHint=false. The description adds real value with the cost signal ('Free') and the optimistic-concurrency contract (revision_conflict plus the current revision in the return). It does not say what happens to a clip already occupying the scene or any permission requirements, which matters for a mutation.

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 cost note, then a single operation sentence, followed by tight Args and Returns blocks. The per-argument text is extremely terse ('project.', 'the scene.'), which saves space without adding much meaning.

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 mutation with no output schema, the description supplies the return shape and the conflict protocol, and the free-form candidate object is addressed by the 'exactly as returned' rule. The main remaining gap is overwrite semantics for an already-populated scene.

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 25%, with just project_id documented, so the description must carry the load. Its Args block covers all four parameters and the critical instruction that candidate must be passed 'exactly as returned', but scene_uid and if_revision are explained only as 'the scene' and 'the revision you read'.

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 ('Put one candidate ... on a scene') and ties the input to the sibling tool studio_stock_candidates. It is clearly distinct from candidate discovery, though it never contrasts with clip-generation alternatives like generate_video_clip.

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?

'Free.' plus the requirement that the candidate come from studio_stock_candidates implies the intended two-step workflow (list candidates, then bind one). It gives no explicit when-not conditions or prerequisites beyond that pipeline hint.

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