Count Messages

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is fully covered by structured data. The description's only additional behavioral signal is that results are aggregated rather than enumerated, which hints at a cheaper call, but it says nothing about what the count represents (total vs. capped) or any limits.

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 sentences, front-loaded with the purpose and immediately followed by the routing rule. No redundant restatement of the name or the schema.

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 an output schema present, the description need not explain the return value, and it correctly focuses on purpose and follow-up. The main gap is that with zero required parameters an empty call silently counts the entire mailbox, and the description never flags that or any scope limit.

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 coverage is 100% across all 20 filter parameters, so the schema already carries the semantics and the description correctly does not repeat them. It adds only the loose phrase 'mailbox filters' and gives no hint about combining filters or the behavior of an empty filter set, so the baseline 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 gives a specific verb and resource ('count messages matching mailbox filters') and explicitly separates the tool from the list-based alternative by noting it works 'without listing every result'. It stops just short of a full contrast statement (e.g. 'unlike mailbox_list_messages, this returns only a total'), so a 4 rather than a 5.

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 names the concrete alternative (mailbox_list_messages) and the exact condition that should trigger a follow-up call: only when examples are needed. That is clear routing guidance, but it gives no inverse guidance about when counting is unnecessary or what to do if the count is zero.

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