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

Beyond the destructiveHint/readOnlyHint annotations, the description adds what actually gets destroyed (the file and its pending webhook events), that the operation cannot be undone, and the specific 'Too soon' failure mode. That is exactly the behavioral context an agent needs before committing to a point of no return.

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?

Three short sentences, front-loaded with the WRITE label and the permanence warning, then the edge case, then the endpoint. No sentence is filler.

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 one-parameter destructive tool with no output schema, the description covers irreversibility, cascading deletion of pending webhook events, and the retry condition. Only a note on what a successful response looks like is absent, which is minor.

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 100% and the docid property already documents the accepted id variants and the format pattern. The description only restates the endpoint path, so it adds little beyond the schema; baseline 3 applies.

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 description opens with an explicit verb and resource ('permanently remove a (signed) document from the OKsign platform') and even labels the operation class as WRITE. This is unmistakably distinct from the read-only siblings (list/get/document_exists) that surround it.

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 gives a concrete condition and remedy for the awkward case: a signed document removed right after its callback may answer 'Too soon', so retry later. It does not explicitly name an alternative or say when removal should be avoided entirely, but for a single destructive action with no near-equivalent sibling, the guidance is clear enough.

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