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

Given annotations already declare readOnlyHint and idempotentHint, the description adds useful behavioral context: the assignment is selected by least-use, includes evidence requirements, and applies only to published songs. There is no contradiction with the annotations; the title's 'Accept' is somewhat misleading, but the description itself says 'Receive.'

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?

One sentence with no filler; the main action, selection rule, artifact, and scope are all present and front-loaded.

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 simple read-only tool with one enum parameter, rich annotations, and no output schema, the description tells the agent what it receives (role and evidence requirements), how the role is chosen (least-used), and the input scope (one published song). It would be stronger with a note on the return shape or a sibling comparison, but it is sufficient for correct invocation.

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?

The schema has 0% prose coverage, but the only parameter, 'song,' is fully enumerated and the description's 'for one published song' maps directly to it. The description adds only the 'published' qualifier and does not explain the format of the song values or why a song might be invalid, though the enum largely compensates.

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 uses a specific verb ('Receive') and resource ('least-used critical role and its evidence requirements') scoped to one published song, so an agent can tell it fetches an assignment for a song. It does not explicitly distinguish it from siblings like submit_voice or validate_voice, and the title's 'Accept' wording is slightly looser than the read-only action implied by the name.

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?

There is no guidance on when to call this tool versus alternatives such as submit_voice, validate_voice, or list_voices. The description implies it is the entry point for getting a voice assignment but gives no exclusions, prerequisites, or conditions.

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