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

Beyond destructiveHint=true, the description makes the irreversible action concrete: 'sends real email and it cannot be recalled' and warns of cross-caller side effects from the shared AgentMail account. This adds operational context that annotations cannot express.

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?

Every sentence earns its place: purpose, irreversible side effect, sender-only scope, shared-account consequence, and the send alternative. The most important operational warning is front-loaded before routing guidance.

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?

For a 13-parameter reply tool with an output schema and annotations, the description covers the non-obvious selection and side-effect context well. It is not perfect because the `reply_all` schema parameter remains unaddressed, which is a completeness gap an agent could stumble on.

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 the baseline is 3, but the description conflicts with the schema's `reply_all` property: the text says this tool answers only the sender while the schema exposes `reply_all` with 'Reply to all recipients.' It also never clarifies whether `to`/`cc`/`bcc` should be supplied for a reply, which weakens parameter understanding for a 13-parameter tool.

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 phrase 'Replies to one message, threading the response correctly, and returns `message_id` and `thread_id`' gives a precise verb, object, and result. It also explicitly names the differentiating sibling for reply-all and send, so an agent can distinguish this tool without guessing.

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 explicitly says this answers the sender only, points to `post_agentmail_inbox_message_reply_all` for every recipient, and recommends `post_agentmail_inbox_message_send` for a fresh recipient set. It even frames reply-all as a 'materially different blast radius,' which is actionable selection guidance.

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