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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: the result ordering, and the warning that results are leads rather than confirmed failures — a semantic nuance annotations cannot express. It does not describe pagination behavior, though the cursor param and output schema cover that.

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 purpose and ordering, then the caveat and remediation workflow. Dense and mostly waste-free, though the final sentence on list_training_gaps is a long clause that a tighter routing pointer could carry.

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 annotations covering the safety profile, a fully documented schema, and an output schema handling return values, the description supplies exactly the missing layer: how to interpret the results and what to do next. Nothing an agent needs to call it correctly is absent.

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?

All three parameters are fully described in the schema (coverage 100%), so the schema does the heavy lifting and the baseline of 3 applies. The description adds no format or range detail beyond what the schema already states.

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 ('List recent conversations that may still need an answer') plus the triage framing, and explicitly contrasts itself with list_training_gaps, which covers the demonstrably-unanswerable case. An agent can distinguish it from list_recent_conversations and list_training_gaps without opening any schema.

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?

Gives ordering semantics (escalated first, then open/pending), an explicit interpretive caveat ('a lead to check, not proof the AI failed'), a follow-up workflow (read the transcript with fetch, check search_knowledge), and names the alternative tool for a different question type. When/when-not and alternatives are all present.

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