follow_ups

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds one genuine behavioral fact beyond that: automated senders and newsletters are filtered out of results. It does not describe ordering, per-category result grouping, or how waiting/to_answer are interleaved, which matters for a two-mode list tool.

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?

A single dense sentence with no filler; the two modes are introduced before the filtering caveat. The opening fragment 'What waits for a reply' is slightly oblique rather than a front-loaded verb, which costs it a point.

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?

An output schema exists, so return shape need not be explained, and the annotation covers the read-only contract. For a five-parameter, all-optional list tool the description gives the conceptual model (two queues, noise filtered) that an agent needs to call it correctly; the only loose end is the undocumented 'account' parameter, which the schema leaves bare.

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 80% and the schema already spells out days, kind, limit and at_least, including their defaults and caps. The description restates the waiting/to_answer meanings that already appear in the kind parameter and adds nothing about the undocumented 'account' parameter or how days interacts with at_least, so 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 defines the resource precisely: conversations where the user wrote last with no reply (waiting) and messages addressed to the user that went unanswered (to_answer). That is concrete enough to separate it from siblings like search_mail or mail_status, though it never states an explicit verb ('list'/'find') and relies on a noun phrase 'What waits for a reply' to convey the action.

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?

Usage is implied rather than stated: an agent can infer this is the tool for 'what needs my reply / what needs their reply' triage. There is one useful scope exclusion ('machines and newsletters aside'), but no guidance on when to prefer search_mail, read_mail, or mail_status, and no mention of what it does not cover.

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