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

Annotations only provide readOnlyHint=false, so the description carries the full burden. It discloses that it repaints pixels, reconstructs the original picture, is real removal (not blur), and that other elements (cuts, timings, transcript, captions) remain unaffected. It also mentions the scope default and project identity return. No contradictions with annotations.

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 description is dense and front-loaded with the key distinction (real removal vs blur) and project-scoping. It's slightly verbose with emphatic caps ('TRULY REMOVE', 'REPAINTS THE PIXELS') but each sentence contributes purpose, usage, or behavior. It could be trimmed without losing value, but it's well-structured.

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 tool with no output schema, it covers purpose, usage, behavior, side effects, and return (project identity with result). It mentions scope default. The main gap is lack of explanation for start/end parameters, but they are likely self-explanatory. Overall, it gives sufficient context for an agent to decide and call correctly.

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% (only project_id has a description). The description adds meaning to scope ('scope defaults to captions') and reinforces project_id as explicit scope. However, start and end parameters are not mentioned in the description, leaving their semantics undocumented. It partially compensates for the low schema coverage but not fully.

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?

The description states a specific verb ('TRULY REMOVE') and resource ('burned-in captions or watermarks'), and clarifies it repaints pixels rather than blurring or barring. It explicitly distinguishes from add_captions and implies it's for text burned into footage, making it distinct from siblings like erase_region or remove_text.

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?

It explicitly lists when to use: for 'remove the captions' / 'take the subtitles off' / 'get rid of the watermark' on burned-in text, and before add_captions to avoid stacking. It also states exclusions ('Cuts, timings, transcript and captions are unaffected') and mentions the project-scoped requirement. However, it doesn't explicitly say when NOT to use alternatives like remove_text or erase_region, so it's clear but not exhaustive.

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