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

With no annotations, the description carries the full behavioral burden and does so richly: an auth/permission gate, binding rate limits (20/hour, 100/day per mailbox), a plain-text-only constraint, and an injection-warning rule. These are exactly the traits an agent cannot infer from the schema.

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?

Three tight sentences: capability first, then routing/permission rule, then safety and limits. No filler, and the most decision-relevant constraint (the permission gate) is front-loaded.

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?

No output schema or annotations exist, yet the description supplies permissions, rate limits, content constraints, and sibling alternatives for a 7-parameter mutation tool. Nothing an agent needs before calling it 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 all seven parameters are already documented with defaults and formats. The description reinforces reply_to_uid and the body/plain-text constraint but adds no syntax or semantics beyond what the schema states, matching the baseline of 3.

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 and resource ('Send an e-mail right away'), clarifies the two modes (new message vs. reply via reply_to_uid), and names the sibling it is not (mail_draft). An agent can distinguish it from mail_draft and mail_read 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?

Gives an explicit precondition (only when the mailbox owner enabled 'the agent may send without my approval') and names the fallback ('otherwise use mail_draft'). Also states the authorization-of-intent rule and the anti-prompt-injection constraint, covering when-not as well as when.

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