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

Annotations already carry the safety profile (not read-only, non-destructive, non-idempotent, closed-world), and the description adds substantial context beyond them: the PROJECT-SCOPED immutability of project_id, that the project identity is returned with the result, and temporal behavior (word binding, held frames starting at word end, allow_speech override). No return format detail or rate limits, but the added context is meaningful.

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?

The scope statement is front-loaded, which is good, but the body is a single dense run-on paragraph of stacked parentheticals with no grouping by device or parameter. It contains no filler, yet the density and lack of structure make it harder to parse than the information warrants.

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 22-param mutation tool with low schema coverage and no output schema, the description covers scope, returned value, device semantics and temporal rules, which is solid. It still omits many parameter meanings and any sibling differentiation, so it is adequate rather than complete.

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 23% on 22 params, so the description must compensate and it does for the semantically hard ones: it glosses kind's enum values, asset_key, src_t, word, focus_from/focus and allow_speech. Many parameters remain unexplained in both schema and description (blur, move, rack_at, density, strength, backdrop, stage, threshold-like numerics), leaving the coverage gap only partially closed.

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 ('add depth effect') and enumerates the distinct devices it produces (parallax 2.5D move, ken_burns 2D move, dof, rack_focus, point_cloud, push_through), which lets an agent distinguish variants internally. However it never names or contrasts a sibling tool (e.g. add_zoom, animate_still, add_subject_effect), so the boundary against neighbours is left for the agent to infer.

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 real when-to-use conditionals per device: push_through 'only when the user asked for a push', held frames 'start as the word ENDS and never sit over speech', and the editorial rule 'one per moment that earns it'. It is missing explicit when-NOT/exclusion guidance naming an alternative tool, so it stops short of a 5.

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