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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the bar is lower. The description adds genuine context the annotations cannot: result ordering, pagination contract (`cursor` = previous `next_cursor` while `has_more`), and the important provenance distinction that web-app audio is included while job-internal clips are not.

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?

Front-loaded with the core statement, then pagination, then WHEN, then scope exclusion — a logical order with no filler. The final parenthetical is dense but carries real disambiguation value, so it earns its place despite slight length.

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 does not enumerate the fields of an audio record, which is the main remaining gap. However, for a simple two-parameter read-only list tool it covers invocation, paging, ordering, and content scope thoroughly enough to call it correctly.

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%, so 3 is the baseline. The description goes slightly beyond the schema by explaining the cursor/next_cursor/has_more relationship as a paging loop, which clarifies how the two parameters interact rather than restating them.

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 ('The account's audio generations, newest first') and adds ordering. Critically, it carves out scope against siblings: top-level account audio including web-app output, but excluding clips other products generate inside a job, which separates it from per-generation tools like get_audio or job-scoped audio.

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 WHEN clause gives concrete triggers ('user asks what they have made', 'you need a voice-over, track or sound effect from an earlier session') and the exclusion sentence defines when-not. It does not name sibling alternatives (e.g., get_audio for a single item, list_voices for voice inventory), so routing is strong but not fully explicit.

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