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

The description repeatedly claims this is 'non-destructive' and that it works 'WITHOUT touching assets or their reference images,' but the annotations set destructiveHint=true. This is a direct contradiction about core side effects, making the description actively misleading rather than transparent.

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 front-loads the core behavior and exclusion, then adds only high-value context: re-scan behavior, follow-up guidance, execution mode, cost, and return value. Every sentence earns its place; there is no filler.

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 single-parameter tool with no output schema, the description is otherwise quite complete: it states the return shape, the behavior on unchanged vs. edited blocks, and the recommended follow-up. However, the destructiveHint contradiction creates a critical gap in safety context, so the description cannot be considered fully trustworthy or 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?

The only parameter, project_id, is fully described in the schema, including its source ('as returned by create_project or list_projects'). Schema coverage is 100%, so the description need not add param-level detail. Baseline 3 is appropriate.

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 names a specific verb ('Re-extract') and resource ('voice blocks from the active script'), and immediately distinguishes itself from scan_script. Even without reading the schema, an agent understands exactly what this tool does and how it differs from its closest sibling.

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?

Explicitly states when to use it ('after a script edit'), names the alternative it replaces (scan_script), and prescribes the follow-up tool (generate_voiceover) for edited blocks. This is model usage guidance with clear conditions and next steps.

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