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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower; the description still adds ordering (most recent activity first), default page size, and explicitly what is NOT returned (no message text or customer details). An output schema exists, so the listed return fields are partly redundant, keeping this from a 5.

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 trigger, then output shape, then pagination; nothing is wasted. It is compressed into very long clauses, which slightly reduces scannability but not content quality.

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?

Given an output schema is present, the description supplies everything else an agent needs: filter semantics, sort order, page size default, and the exclusions. Nothing required for a correct invocation is 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 100%, so each of the four parameters is fully documented in the schema, making 3 the baseline. The description only restates the website filter ('optionally for one website') and adds no syntax, default, or edge-case detail beyond the schema.

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 (list) and resource (customer conversations) with the exact scope — open, unread or recently active, optionally per website. An agent can distinguish it from get_conversation and get_unresolved_conversation_counts 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?

Opens with an explicit trigger ('Use this when someone asks which customer conversations are open, unread or recently active') and closes with an explicit exclusion ('Not for open-conversation totals'), routing the agent away from the counts sibling. When-to-use and when-not are both present.

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