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

Beyond the destructiveHint/openWorldHint annotations, the description discloses that destruction is irreversible after fulfillment, that safe retries return the original request, and that a confirmation and idempotency key are required. Some of the closing text (Canonicality, 'inspect refreshed state before retrying') is generic boilerplate rather than tool-specific behavior, keeping this short of a 5.

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 paragraph pads with repeated statements: the confirmation requirement appears in the second sentence and again in the 'Confirmation boundary' sentence, and the Canonicality/Idempotency clauses are reusable boilerplate that does not earn its space for this specific tool.

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, open-world mutation with no output schema and only 20% schema coverage, the description covers the critical gaps: irreversibility, auth prerequisite, confirmation boundary, and retry semantics. It stops short of describing what the queued request returns or how the shred is fulfilled, but the essentials are 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 only 20%, so the description has to carry meaning, and it does for three of five params: confirm must be a fresh confirmation for the exact item, idempotencyKey must be stable with retries returning the original request, and mailItemId is pinned to 'one exact mail item'. companyId and the nested _corply_context object are never explained.

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 first sentence names a specific verb and resource ('Queue secure physical destruction of one exact mail item') and adds the scope constraint 'one exact', which separates it from bulk operations. It never names the adjacent mail siblings (request_mail_forward, request_mail_scan), so the agent gets a clear purpose but no explicit differentiation from alternatives.

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 states the precondition for calling: obtain fresh founder confirmation for the exact item, then call with confirm:true and a stable idempotencyKey, plus an authenticated active company access prerequisite. There is no explicit 'when not to use this' or comparison to request_mail_forward/request_mail_scan, so guidance is clear but not exhaustive.

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