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

With no annotations, the description carries full behavioral burden. It discloses returns ('per-step verdict, flagged errors, suggested corrections') and an on-chain certificate side effect. It does not mention authorization/cost but is otherwise transparent for an audit-style tool.

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 three concise, action-first sentences with no redundancy. Every sentence adds value: what it does, when to use it, and what it returns/accomplishes.

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 description covers return values, use case, and an on-chain outcome; the output schema covers structured return details. Minor gaps exist around what 'approved' means and on-chain mechanics, but the overall guidance is complete enough for an agent.

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 100%, so the baseline is 3. The description adds tool-level context ('mid-chain errors', '3+ steps'), but this is not parameter-specific and slightly conflicts with the schema's minItems=2.

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 states a specific verb ('Audit') and resource ('your step-by-step reasoning') with a precise scope ('mid-chain errors') and timing ('before producing the final answer'). This clearly distinguishes it from sibling review/verify tools like review_content and verify_external_source.

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 explicitly says when to call: 'when stakes are high and your chain has 3+ steps' and 'before producing the final answer'. It contrasts with 'final-output checks' but does not name specific alternative sibling tools or provide an explicit when-not-to-use statement.

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