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

Annotations declare readOnlyHint=true and idempotentHint=false; the description reinforces this with 'Nothing is saved or published', which is valuable confirmation that side effects are zero. It does not, however, disclose that repeated calls may yield different output (consistent with idempotentHint=false) or whether credits are consumed by AI generation.

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 short sentences, front-loaded with the action and the no-side-effects guarantee, with the sibling routing packed into the close. No filler.

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?

The description does convey the essential shape of the result (suggested Q&A pairs) and that nothing persists, which matters given there is no output schema. But with three undocumented parameters and no note on credit cost or output variability, key calling details are missing.

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 description coverage is 0%, so the description carries the full burden, yet it never mentions profile_id, category, or instructions. The agent gets no hint about what 'category' scopes or how 'instructions' steers the generated Q&A.

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 (suggest) plus resource (question-and-answer pairs) for a profile, and explicitly frames the output as unsaved AI drafts. It also names the related siblings list_faqs and request_publish_faq, so an agent can place it precisely in the FAQ workflow without opening other 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?

'Nothing is saved or published' establishes when to use this tool versus the mutating siblings, and it routes publishing to request_publish_faq and stored-FAQ reading to list_faqs. It stops short of an explicit 'do not use this when...' clause, but the alternative mapping is clear.

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