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

Annotations already declare this a safe, idempotent read, so the description needn't restate safety. It adds genuinely useful behavior instead: newest-first ordering and the coverage limit that mail reaching no connected mailbox is absent. What it omits is anything about paging cost or volume, though the schema covers the cursor mechanics.

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 resource and ordering, then the alternative and the caveat. The first sentence is long because it enumerates returned fields, but each clause carries distinct information rather than 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?

With no output schema, the description carries the burden of describing the return shape, and it does so field by field. Combined with a fully documented parameter schema and read-only annotations, what remains missing is marginal detail such as page size caps already handled by the schema.

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%, so limit, cursor, and lead_id are already fully documented in the input schema. The description only reinforces the scope of lead_id by saying "one merchant" and says nothing about the cap or cursor beyond what the schema states. Baseline 3 is appropriate.

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 names a specific resource (the email exchange with one merchant) and its ordering, and enumerates what each item carries: sender, subject, file names, whether a reply is outstanding, and a preview. It also explicitly contrasts itself with get_email, so an agent can separate a list of messages from a single full message without opening either 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?

"Use get_email for one in full" gives an explicit alternative and the condition that selects it. It also warns that a quiet exchange is not evidence of no reply, which steers the agent away from a wrong inference. What it does not address is how this relates to search_emails for cross-lead or keyword lookups.

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