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

Annotations already declare destructiveHint=true and idempotentHint=true, so the bar is lower, but the description adds genuinely new behavior: that unfinished work is cancelled as a side effect and the action is irreversible. It still omits how the idempotency key is used and what confirmation entails in practice.

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 brief sentences, with the destructive action and its side effect front-loaded and the irreversibility caveat immediately after. 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?

An output schema exists, so return values need no explanation, and annotations cover the safety profile. But for a destructive three-parameter tool with zero schema coverage, the description leaves parameter usage and idempotency semantics unexplained.

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 0%, so the description must carry the load, yet it never mentions project_id or idempotency_key. "Confirm" loosely hints at the confirmed boolean, but two of three parameters are left entirely undocumented.

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 (delete) and resource (project/audio) plus an additional effect (cancel unfinished work). It does not name the closely related sibling delete_edit or explain how the two differ, so an agent must infer which delete to pick from context.

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?

"Confirm; cannot be undone" tells the agent a confirmation step is required and warns of permanence, which is usable context. However it gives no guidance on when to prefer this over alternatives like cancel_batch or delete_edit, leaving the selection decision implicit.

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