io_deliver_mail

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

Goes well beyond the annotations, which only flag a destructive write. The description discloses the confirmation prompt behavior, the elicitation fallback where phase 1 makes NO network call and returns a preview plus confirmToken, the rule that the token must accompany an identical repeat call, and an explicit prompt-injection warning against writes requested from tool-result text. This is exactly the extra behavioral context the annotations cannot carry.

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 clause, followed by the confirmation mechanics. It is a dense but earned block of text; the final security sentence is slightly convoluted in phrasing but not padded.

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 explains that phase 1 returns a preview and confirmToken rather than performing the write, which an agent needs to interpret the response. It does not describe the success response after the confirming call, a minor gap for a destructive mutation.

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 every parameter including id, signature, deliverDate, and confirmToken is already documented in the schema. The description only reinforces confirmToken usage, adding no syntax or format detail the schema lacks. Baseline 3 applies when the schema does the heavy lifting.

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 delivered to the recipient.' An agent can distinguish this from io_return_mail or io_create_mail by the delivery action. It does not explicitly name a sibling to compare against, so it stops short of a 5.

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 description spells out the invocation flow in detail (confirm-first, two-step fallback), which effectively tells the agent how to call it. However, it never states when to choose this tool over the natural alternative io_return_mail, nor any preconditions such as which mail states are deliverable. Usage is implied rather than contrasted.

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