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

The annotations already declare the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false, openWorldHint=false). The description's one genuine addition is the side effect: removal also takes the scene's owned caption suppression, which is real behavioral context not present in the structured fields. It does not say whether the removal is undoable, what happens if the id is unknown, or whether the caption suppression is restored on re-add — gaps that matter for a mutation tool flagged non-destructive.

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?

A single front-loaded sentence with no filler; the primary effect comes first and the cascade effect second. Nothing can be removed without losing information.

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 and half its parameters undescribed, the definition covers the essential effect and cascade but omits failure behavior and return information. An agent could invoke it, but not confidently predict the result or error conditions.

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 only 50%: project_id is documented in the schema while id has no description. The description only faintly compensates, implying via 'identified' that id must reference an existing scene, but never states the id type/format or that it is the scene identifier rather than a caption id.

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 a specific resource ('Removes an identified native typography scene'), and adds the cascade detail that owned caption suppression goes with it. This distinguishes it from remove_typeset, remove_text, remove_ui_scene, and set_typography_scene by resource name, though it never names those siblings explicitly.

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?

There is no when-to-use or when-not guidance, no prerequisite statements, and no pointer to alternatives such as set_typography_scene for editing or remove_typeset for a different artifact type. An agent must infer the usage entirely from the tool name and the word 'identified'.

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