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

With no annotations at all, the description carries the full burden, yet it omits whether the message is delivered immediately, whether it triggers human action, whether it is queued, and whether it consumes credits or has rate limits. Only the fact that it is a write to a third party is conveyed.

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 short sentence, but its brevity comes from omission rather than discipline. Every substantive detail an agent needs is absent, so there is nothing front-loaded to work with.

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 5-parameter write tool with zero annotations and no output schema, the description should explain delivery semantics, required vs optional fields, and its relationship to contact_human. None of that is present.

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 20% (only api_key is documented) across 5 parameters, and the description mentions none of them. It does not clarify the required body, nor explain what subject, item_id (presumably linking the message to an order/item), or request_id are for.

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?

"Write to the human who handles your mail" gives a verb (write) and a target (the human), so the basic intent is graspable, but it never uses the tool's own name or says this is a messaging/notification channel. Critically, the sibling set contains 'contact_human', and the description does nothing to distinguish these two tools.

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?

There is no statement of when to use this versus alternatives, no prerequisites, and no exclusions. Given a sibling literally named contact_human, the absence of any routing guidance is a real defect for an agent choosing between them.

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