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

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint false), the description adds critical behavioral traits: 'never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"}' and 'Every call is read-only and idempotent, so after correcting the input it is always safe to retry.' This explains error handling and retry safety, which annotations do not cover.

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 dense but not overly long. It is front-loaded with the main purpose in the first sentence. Each subsequent sentence adds useful detail (output fields, usage context, error behavior). There is no fluff, but it could be slightly more concise by combining some ideas. Still, it is well-structured and efficient.

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 the tool's complexity (nested objects, output schema, premium license), the description covers all necessary aspects: purpose, input, output, error handling, workflow sequence, and sibling relationships. It mentions the typical return format and the integrity_note, which is helpful even though an output schema exists. The description is complete for an agent to use the tool correctly.

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 coverage is 100% with good descriptions for both parameters. The description adds value by explaining the effect of the fingerprint parameter: 'when a voice_fingerprint result is supplied, adds numeric targets to hit that person's voice.' It also provides a concrete example of typical input, which helps the agent understand how to use the parameters together. This goes beyond the schema's static type definitions.

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 the tool's purpose: 'Produce a precise rewrite brief that de-AIs a draft, with numeric targets.' It lists specific outputs (edit_list, numeric_targets) and distinguishes itself from siblings like verify_rewrite and ai_tell_scan, making the tool's unique role obvious.

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 tells when to use the tool: 'Use after a scan has identified what to fix; returns a brief, not rewritten prose.' It also tells when not to use it: 'Not for checking whether a rewrite worked (verify_rewrite).' Additionally, it provides a workflow hint: 'Apply the brief with your agent, then confirm with verify_rewrite.' This is comprehensive guidance.

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