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

The description does not contradict the annotations: readOnlyHint=false, openWorldHint=true, destructiveHint=false. It adds useful behavioral details beyond the annotations by specifying the 5 MESH/call cost, the three return components (assertion, minimal revert, non-vacuity confirmation), and the logical guarantee that the assertion cannot pass vacuously. It does not disclose side effects, failure behavior, or authorization needs, though the annotations reduce that burden.

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 purpose is front-loaded and the return format is clearly stated. However, the indexOf example is a lengthy illustration that may distract, and 'Full input contract: this tool's input_schema' is meta-content rather than useful description. Overall it is reasonably compact but not exceptionally tight.

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 subtle, methodology-heavy tool with no output schema, the description explains the concept and returns but omits the key operational detail: what the caller must put in the generic input object for negative-control. It also lacks an example invocation or explicit conditions for use. Because the input schema is generic and the description merely defers to it, an agent would struggle to call this tool correctly despite understanding the concept.

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 100% description coverage on its single input parameter, so the baseline is 3 even though the tool description adds no specific input syntax. In practice, the schema's parameter description is generic ('Capability-specific payload') with examples for other tools, not for negative-control, so the agent still lacks the exact payload contract. The description's pointer to the input schema adds no extra meaning.

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 states the exact purpose: prove a fix is real by writing a test that goes RED when the fix is reverted. This is a specific verb + resource and clearly separates the tool's falsification-oriented role from generic test-generation tools. It does not, however, explicitly distinguish it from sibling tools like refutation-pass, which may serve a similar negative-testing function.

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?

No explicit when-to-use, when-not-to-use, or sibling alternatives are provided. The reader can infer that it is for validating a fix, but the description never states the trigger conditions or excludes cases where another tool would be more appropriate.

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