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

Annotations declare readOnly, idempotent, and non-destructive. The description adds the decision rule: DONE requires affirmative completion evidence, NOT_DONE requires affirmative non-execution evidence, otherwise UNKNOWN. This provides valuable behavioral context beyond the annotations, with no contradiction.

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 description is two sentences, front-loaded with the when-to-use context, and each word contributes meaning. The reference to 'POSTFACT' is slightly unexplained but does not waste words.

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 9 parameters, a nested evidence object, and no output schema, the description is insufficient. It covers the high-level decision logic but omits parameter semantics and return format, leaving an agent with significant gaps in knowing how to construct a request or interpret the response.

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 has 9 parameters with zero description coverage, and the description offers no parameter-level guidance. The mention of 'evidence' is conceptual, not mapped to the evidence object structure. An agent would be unable to correctly populate or interpret parameters like method, status, requestId, or sideEffect.

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 clearly states that the tool resolves ambiguous side effects after a side-effecting action fails, and specifies the three possible outcomes (DONE, NOT_DONE, UNKNOWN). This makes the purpose specific and distinguishable, even in the absence of sibling tools.

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 explicitly provides the trigger condition: call after an ambiguous failure and before retrying. It does not mention when not to use, but the context is sufficient for an agent to decide. No alternative tools are listed, so exclusion criteria are not needed.

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