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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds genuinely new behavioral context beyond the annotations: the filtering rule that greetings and very short messages are excluded, and the fact that answer_feedback is computed over the same window as the gap signals.

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?

The purpose is front-loaded in the first clause, and the rest is dense with distinct facts (signals, return composition, workflow, exclusion rule). It is slightly long, and the detailed enumeration of return contents partly duplicates the output schema, but no sentence is 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?

For a complex analytical tool with an output schema, annotations, and fully documented parameters, the description supplies everything an agent still needs: what counts as a gap, the exclusion rule, the pagination hint, and how to act on the results via sibling tools.

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 100%, so days, limit and cursor are already fully documented in the schema, including defaults, ranges and cursor semantics. The description only contributes the 'same window' tie between the lookback and answer_feedback, so the baseline of 3 applies.

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 precise verb+resource ('Find questions the AI could not answer well') and then enumerates the exact signals that qualify a question as a gap: AI fallback replies, human escalations, and 1-2 CSAT ratings. That specificity distinguishes it from vaguer siblings such as list_unanswered_questions, which only covers one of those signals.

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?

It gives a clear decision context ('Use it to decide what to teach next') and names the follow-on tools and order of operations (check search_knowledge, draft, then add_trained_answer). It stops short of explicitly stating when NOT to use this tool versus list_unanswered_questions, which appears to be a close sibling.

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