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

Beyond the annotations, it discloses a full two-phase confirmation protocol: the call is only PROPOSED, returns status='confirmation_required' with an action_id and plan_token, and the write occurs only after confirm_action. This is exactly the operational context the destructiveHint annotation cannot convey.

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 short sentences, front-loaded with purpose, then the irreversibility limit, then the confirmation mechanics. No filler or repetition.

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 usefully documents the confirmation response shape and the follow-up tool. The remaining gap is sourcing the scheduled_id and any note on whether a cancelled send can be rescheduled.

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 0% and the description never mentions scheduled_id — not its meaning, format, or where to obtain it. The single parameter is inferable from its name, but the description adds no compensating meaning for an undocumented field.

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 states a specific action on a specific resource in plain terms: 'Call back a letter that has not gone out yet,' i.e. cancel a scheduled send. The clause 'Once it has been sent this can do nothing — there is no unsend' cleanly separates it from send-side siblings such as mail_send or mail_schedule_send.

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 gives an explicit precondition and an explicit exclusion: the message must not yet have gone out, and after sending the tool is useless. It does not name an alternative for locating a pending message (e.g. a list-scheduled sibling), which keeps it short of a 5.

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