io_return_mail

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

Annotations only say destructiveHint=true/readOnlyHint=false; the description goes far beyond that by disclosing the two-phase confirmation flow, that phase 1 makes NO network call, the meaning and one-time nature of confirmToken, the elicitation-vs-fallback branching, and an explicit prompt-injection warning. This is exactly the behavioral context an agent needs before performing a destructive write.

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?

Purpose is front-loaded in the first sentence, followed by the confirmation mechanics. Every sentence carries information, though the final prompt-injection sentence is grammatically awkward and takes a second read to parse.

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?

There is no output schema, and the description covers the phase-1 response shape ('preview' plus 'confirmationToken') and the confirm-mode branching, which is the hard part of calling this tool correctly. It stops short of describing the eventual success response or error cases, but nothing essential for correct invocation 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 id, reason, and confirmToken are already fully documented in the schema. The description reinforces the confirmToken contract (never on first call, never reused, ignored under elicitation) but adds no new field-level meaning beyond that baseline.

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: 'Mark an iOffice mail item as returned to sender.' This is clearly a state transition on a mail item, distinguishable from io_list_mail/io_get_mail/io_create_mail. It does not explicitly contrast itself with the closest sibling, io_deliver_mail (the other mail state transition), so it falls short of full sibling differentiation.

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?

The when-to-use condition is implied (after the user confirms) and the confirmation protocol is spelled out well. However, there is no guidance on when to choose this over alternatives such as io_deliver_mail or how it fits alongside io_get_mail/io_list_mail, so usage against siblings is left to inference.

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