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

Annotations already declare readOnly/idempotent/non-destructive and closed-world, and the description adds substantial behavior beyond them: a hard cap of 100 rows, that counts may be lower bounds flagged by results_limited, that counts should be reported from counts rather than rows, and that a reply pauses the contact's follow-ups while out-of-office/not-now replies can resume them. That is real domain behavior an agent could not infer from the structured fields.

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?

Highly information-dense with the core scope front-loaded in the first sentence and no filler. Some later clauses are telegraphic to the point of ambiguity ('Say how many from counts, not rows', 'a closed_only reply only needs marking done'), which costs a little readability but not much 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, yet the description covers the returned fields, the row cap, lower-bound counts, and the alternate positive mode, which is most of what an agent needs. Remaining gaps are the meaning of counts/results_limited/closed_only as structured fields and the absence of any timezone mention, so it is strong but not airtight for a single-parameter, nested-input tool.

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?

Top-level schema coverage registers as 0% (the single 'query' object carries no description), so the description must compensate; it does explain the positive_since/positive_until window and that it replaces the default awaiting-user listing. However, it never explains that these live inside a query object, never mentions timezone despite the schema having one, and references positive_contacts without clarifying it is a returned field rather than a parameter, leaving real ambiguity about the input shape.

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 plus the exact scope ('up to 100 open or snoozed replies awaiting the user') and enumerates the fields returned: contact, company, classification, priority, due time and suggested response. It also defines the boundary of what is not returned (done, automated, bounce, opt-out), so the agent can distinguish this from other list_* siblings without opening the 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 explicit conditional guidance: use positive_since/positive_until to list every positive reply including resolved ones instead of the default awaiting-user queue, and use closed_only replies only for marking done. It also explains the required follow-up action per classification (sequence_stopped vs sequence_completed). It stops short of naming any alternative tool for replies that fall outside these modes, so it is clear but not fully routing.

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