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

Annotations already declare destructiveHint=true and openWorldHint=true, but the description adds genuinely non-obvious behavior: possible handling charges, exposure of correspondence contents in the authenticated browser, and that safe retries return the original request. This cost/privacy/idempotency detail goes meaningfully beyond the annotations.

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?

The core action is front-loaded well, but the text is padded with boilerplate blocks ('Canonicality', 'Idempotency', 'Confirmation boundary') that restate the earlier confirmation requirement and add jargon without new meaning. Several sentences could be cut without losing information.

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 destructive, no-output-schema mutation the description covers the important agent-facing concerns: confirmation, idempotency, cost, prerequisites, and retry semantics. The remaining gap is the undocumented companyId and context parameters, but the behavioral picture is otherwise complete.

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 coverage is only 20% and 5 parameters exist, so the description must carry weight. It clarifies confirm:true, idempotencyKey stability, and implies the exact mailItemId, but says nothing about companyId or the _corply_context object. It partially compensates but leaves two params undocumented.

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 phrase and resource: 'Queue Corply Ops to open and scan one exact received mail item.' An agent can distinguish this from sibling mail operations like request_mail_forward or request_mail_shred by the action. However it does not explicitly name or contrast with those siblings, which would be needed for 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?

Gives a precondition ('obtain fresh founder confirmation for the exact item before calling') and a prerequisite (authenticated active company access), which is useful when-to-use context. But it never states when to prefer this over the sibling request_mail_forward/request_mail_shred or get_mail_item, so routing 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.