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

The description adds significant value beyond annotations. It confirms read-only and idempotent behavior ('Every call is read-only and idempotent'), explains error handling in detail ('never raises a protocol error — it returns {"error": ...}'), and mentions it is FREE. No contradictions with annotations.

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 well-structured with front-loaded purpose and key usage. It includes a usage example, return format, differentiation, error behavior, and safety notes. While every sentence adds value, it could be slightly more concise (e.g., condensing the error explanation). Still very good.

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 (2 params, 100% schema coverage, output schema present, complete annotations), the description fully covers input requirements, output structure, error handling, usage scenarios, and side-effect safety. No gaps remain for an agent to select and invoke 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 descriptions for both parameters. The description adds a concrete example of typical input ({"samples": [...]}), explains the 150+ word requirement, and notes the label parameter's default. This enriches understanding beyond the schema.

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 and resource: 'Build a measurable voice profile from samples of a person's real writing.' It clearly distinguishes from siblings by naming ai_tell_scan as the tool for scoring unknown drafts, and by directing use with humanize_plan/verify_rewrite.

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?

Provides explicit when-to-use: 'Use on samples the person actually wrote.' Also states when not to use: 'Not for scoring an unknown draft (ai_tell_scan) and not on text the person did not write.' Recommends feeding result to sibling tools, giving clear context.

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