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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description correctly spends its words elsewhere: cost ('free'), pagination ceiling (100 rows plus up to three earlier receipts), cursor mechanics, and owner/organization scoping. That is meaningful behavior an agent cannot read off the annotations, though return shape beyond 'rows' is not described.

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?

Short, front-loaded with the action and its timing, then dense operational facts in single clauses. 'Follow _links.next' is a compact and useful pointer to the output field. Slightly choppy, but nothing is padding.

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 no output schema, the description carries the return burden and does so adequately: page size, extra receipt rows, and the _links.next cursor. Auth scope (owner plus active organization) is stated. Only the guest_token path and the actual row fields remain 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 coverage is 75%, and the description adds genuine semantics beyond the schema by stating that language and source filters must be carried forward when following the cursor, which is exactly the pitfall an agent would hit with id/language/after. The undocumented guest_token is left unaddressed.

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 list operation on a specific resource ('saved audits prompts'), which the name and the 'audits' qualifier scope apart from the domain/site fix-prompt siblings. It stops short of naming those siblings (list_domain_fix_prompts, list_site_fix_prompts) so the differentiation rests on the tool name rather than the prose.

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?

'before generation' and 'Listing is free' imply the intended moment to call this (check for existing saved prompts instead of paying for generation), which is a real usage cue. There is no explicit when-not, no prerequisites, and no named alternative such as generate_fix_prompt or get_fix_prompt.

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