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

Annotations already declare readOnly=false, idempotent=true, destructive=false, so safety is covered. The description adds context the annotations cannot: a cascade side effect (also removes the scene's owned caption suppression) and the return behavior (project identity is returned with the result). It stops short of describing failure modes or error behavior.

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 sentences with no filler, and the scope constraint is front-loaded as a labeled prefix. Arguably the core action being stated second weakens the front-loading slightly, but nothing is 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?

For a two-parameter mutation with no output schema, the description covers scoping and declares the return value, which is exactly the gap an absent output schema leaves. The remaining gap is the unexplained `id` parameter and the lack of any failure/precondition note.

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?

With only 50% schema description coverage, the description must compensate and does not. The project_id parameter has a detailed schema description that the prose merely restates, while the required `id` parameter is undocumented in both the schema and the description — an agent cannot tell what identifier form it needs.

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 a native typography scene") and adds a distinguishing detail — that the scene's owned caption suppression goes with it. It is clearly separable from set_typography_scene, but it doesn't explicitly distinguish itself from other removal siblings like remove_text or remove_editorial_graphic beyond the word "typography".

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 PROJECT-SCOPED preamble tells the agent it must supply an explicit project_id and that the active-project pointer is never used, which is real usage guidance. However, there is no when-to-use/when-not guidance, no prerequisite conditions (e.g., the scene must exist), and no routing to alternative removal tools for other graphic types.

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