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

Annotations already declare destructiveHint=true and idempotentHint=true, yet the description adds substantive context beyond them: the audio and timing files are erased, restoring requires re-synthesis that spends credits, and repeated deletion is a no-op. This is exactly the kind of consequence disclosure an agent needs before calling a destructive tool.

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?

Every sentence earns its place: trigger, return value, irreversibility/cost, idempotency, and exclusion are each stated once with no filler. The trigger is front-loaded so the agent can decide quickly.

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 destructive tool with an output schema, the description covers everything needed: what is destroyed, the cost of reversal, idempotent behavior, and the sibling it must not be confused with. Nothing material 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?

With a single parameter at 100% schema description coverage, the schema already fully documents speechId. The description adds no format, syntax, or lookup guidance beyond what the schema provides, so the baseline of 3 applies.

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 gives a specific verb and resource ('one voiceover line permanently deleted with its audio') and explicitly distinguishes the tool from its sibling update_speech by stating 'Not for changing its words.' An agent can identify the exact operation and its scope without opening the schema.

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 states a clear trigger condition ('when someone wants one voiceover line permanently deleted') and an explicit exclusion ('Not for changing its words'), which routes the agent toward update_speech. However, it does not name the alternative tool directly, leaving a small inference step.

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