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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description adds critical context beyond them: the deletion is permanent and irreversible, it also removes all box versions, and there is a mandatory two-step confirm protocol. It also disambiguates the claim_token path, which no annotation conveys.

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 sentences, zero filler. The irreversibility warning and the operational procedure are front-loaded in the order an agent needs them: what it deletes, then how to do it safely.

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?

With an output schema present, return values need no explanation, and the description covers everything else an agent needs: both authorization modes, scope of deletion (all box versions), reversibility, and the confirmation gate. Nothing material is missing for a destructive tool with three params.

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 67% and the schema already describes 'confirmed' and 'claim_token', yet the description ties them to a concrete workflow (pass claim_token for account-less songs; re-call with confirmed: true after confirmation), adding meaning beyond the field-level text. song_id itself is left unexplained, but it is self-evident.

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 and resource ('Permanently deletes ... songs') plus the exact scope: the signed-in person's song with all its box versions, or an account-less song via claim_token. This distinguishes it clearly from write siblings like create_song and add_version without needing their schemas.

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 covers both usage paths (signed-in vs. claim_token) and prescribes the confirmation workflow: tell the person which song will be deleted, get confirmation, then call again with confirmed: true. This is a complete when/how instruction rather than an implied one.

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