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

No annotations are provided, so the description carries the behavioral disclosure burden. It explicitly states that history is preserved and that future public reads are denied, which tells an agent this is not a hard delete. It does not cover version-mismatch behavior or authorization requirements, but the key effects are disclosed.

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?

Two short sentences: the first states the action, the second states the two key consequences. There is no filler, no repetition of schema fields, and the most important information is front-loaded.

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?

The core behavior and post-conditions are present, and the description is minimally viable. However, with three required parameters, no output schema, and no annotations, the missing idempotency-key semantics and version-mismatch behavior are meaningful gaps that prevent it from being fully 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?

The schema provides no descriptions for any of the three required parameters, and schema coverage is 0%, so the description must compensate. It adds meaning for expectedVersion through 'current expected version' and weakly for id through 'your evidence', but idempotencyKey is completely unexplained, leaving an agent uncertain how to construct or reuse it.

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 verb 'withdraw' plus the resource 'evidence' makes the action unambiguous, and 'with its current expected version' adds useful concurrency context. It does not explicitly reference sibling tools like submit_evidence, but the purpose is clear enough without that 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 phrase 'your evidence' implies the tool is for withdrawing your own evidence, and 'current expected version' hints at a precondition. However, it does not state when to choose this over alternatives, nor does it mention exclusions or prerequisites beyond the version requirement.

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