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

Annotations declare the mutation profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false); the description adds genuinely new behavior: a new song record is created and the return is a short-lived (expiring) upload ticket. It does not cover permissions or what happens if the ticket expires, but the added context is real.

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, front-loaded with the action and the returned artifact, with the caller guidance second. Slightly wordy in the second sentence but nothing is wasted.

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?

No output schema exists, and the description usefully summarizes the return value (a short-lived ticket for uploading). Combined with the caller guidance, an agent has enough to decide correctly, though expiry handling and the relationship to the subsequent mastering step are left implicit.

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 50%: genre is exhaustively documented in the schema, while title has no description. The description only hints that the title derives from the file the person checked in, which slightly clarifies the required param but adds no genre guidance beyond the schema.

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 states a concrete verb and resource (creates a new song, returns an upload ticket) and adds the outcome (enables mastering the full song). It is clear what the tool does, though it never names the closely related siblings (create_song, master_song, start_mastering) to disambiguate.

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?

"The studio calls this tool when the person chooses to master the full song" gives an explicit trigger condition, and "the assistant does not need to call it directly" gives an explicit non-use case. What is missing is routing against alternatives like master_song or start_mastering, which an agent could otherwise confuse it with.

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