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

Annotations already declare write (readOnlyHint=false), idempotentHint=true, and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-derived context: the call is scoped strictly to the explicit project_id and returns the project identity alongside the result, and it discloses a non-obvious side effect — the footage occupying the removed scenes' slots is removed too. The only tension is that 'remove ... footage' sits awkwardly beside destructiveHint=false, though taken as timeline-reference removal rather than source-media deletion it is consistent.

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?

Two short sentences, both front-loaded with the highest-value tokens ('PROJECT-SCOPED', 'WRITE', 'remove UI scenes ... by id'), with no filler. The ALL-CAPS labels are slightly templated but the whole definition is only ~30 words and every clause earns its place.

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 2-parameter write tool with no output schema, the description covers scope, side effect, and result identity, and annotations supply idempotency and safety. It stops short of stating failure behavior for nonexistent ids or required permissions, but nothing essential to invoking 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 coverage is 50%: project_id is fully documented in the schema (including where to copy the id from), while ids is bare. The description partially compensates by saying removal is 'by id' and that ids identify UI scenes, but it gives no format, cardinality, or behavior for unknown ids. Baseline 3 for the schema doing half the work.

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 ('remove UI scenes ... by id') and even names the side effect on slot footage, so an agent knows exactly what it deletes and how ids map. It does not, however, differentiate itself from same-family siblings such as remove_typography_scene or remove_vector_graphic, which share the same pattern.

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 description carries a scope constraint (must pass an explicit project_id, never the active-project pointer) but gives no when-to-use or when-not-to-use guidance relative to the many other remove_* tools. There is no routing information for an agent choosing among 20+ removal siblings.

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