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

Annotations already declare destructiveHint=true, so the description must add beyond that — and it does: output artifacts are also removed, the deletion is best-effort ('attempts to'), and the action is irreversible with a confirmation requirement. Minor gap: no mention of behavior when the ID doesn't exist or when output deletion fails.

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 short sentences, the scope of deletion first, then the irreversibility and confirmation warning. No filler; every clause carries operational weight.

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 delete with no output schema, this covers what an agent needs: what gets destroyed (including derived output), that it's permanent, and that user confirmation is required. Only the error/not-found case is unaddressed.

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 100% and the id property already documents its meaning and origin (returned by POST create APIs). The description mentions no parameter details, so it adds nothing beyond the schema — baseline 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?

States a specific verb (deletes) and resource (audio project), and adds that it also removes the completed output, which distinguishes it from a mere record cleanup. The 'audio' qualifier separates it from delete_image_project and delete_video_project, though it doesn't name them.

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?

Gives an explicit precondition: 'confirm with the user first', which is the key gating instruction for an irreversible action. It does not name alternatives or say when-not to use it, but no real substitute exists among the siblings for removing an audio project.

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