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

Annotations already provide readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the core safety profile is covered. The description adds behavioral context by stating that errors return a structured error object instead of protocol errors, and that all calls are read-only and idempotent. However, this doesn't go significantly beyond what the annotations plus schema already convey. The description does not contradict any annotation, so no contradiction flag.

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 front-loaded: the first sentence states the core purpose and the premium license. Subsequent sentences provide details on how it works, typical input/output, when to use, and error behavior. Every sentence serves a distinct purpose—no redundancy. It is tightly written for the amount of information conveyed.

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?

Given that the tool has an output schema (context signals indicate one exists) and annotations cover safety, the description effectively completes the picture: it explains the purpose, usage scenarios, alternative tool, expected input/output format, error handling, and retry safety. For a tool with 3 parameters (2 required) and nested objects, this is fully adequate. No gaps remain.

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 goes beyond the schema by showing the exact JSON input format expected (e.g., '{"original": "<draft>", "rewrite": "<edited draft>"}') and the expected output fields (score_before, score_after, score_delta, content_word_retention_pct, remaining_tells, verdict). This adds significant semantic value by linking parameters to the verification logic and output structure.

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 starts with a clear verb phrase 'Verify a rewrite actually improved' and explicitly lists the three dimensions of verification: score delta, meaning check, and voice distance. It distinguishes itself from the sibling tool 'ai_tell_scan' by stating that this tool compares before and after, while that tool is 'for scoring a single draft'. The mention of 'PREMIUM (license)' further clarifies access restrictions.

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 states when to use this tool: 'Use only when both the before and the after text are available'. It also provides a clear alternative: 'Not for scoring a single draft (ai_tell_scan)'. Additionally, it notes the error behavior: on invalid input, it returns an error object rather than raising a protocol error, and advises that calls are read-only and idempotent so retrying is safe after correcting input.

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