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

The description discloses the exact output format (per-item pass/warn/fail, principle ids, concrete issues, before→after rewrite, aggregate summary) and the nature of the heuristics (robs requires number+unit, CTA length constraints). It also states it is completely offline, which the annotations do not mention. Annotations already mark readOnly/idempotent, so this extra context enhances trustworthiness.

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 a single, dense sentence that compresses a good deal of information—output, heuristics, and alternatives—without superfluous words. It could be split into a second sentence for readability, but it is clearly structured and earns its length.

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 is read-only, has no output schema, and has intricate behavioral rules, the description suffices: it specifies what is returned, the nature of the heuristics, and even the no-network constraint. It lacks explicit error-handling or batch-size limits, but these are not critical for a self-contained auditing tool.

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 schema already documents all three parameters. The description adds heuristic–type mapping (e.g., 'metric items must carry a number+unit', 'prose flags passive voice'), which explains how the type parameter influences evaluation. However, it does not add code-level detail for goals or system beyond what the schema states, so it stays at the baseline 3.

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 verb ('Evaluate') and resource ('an array of content items... against UX-writing principles'), and explicitly distinguishes it from sibling 'evaluate_design' by specifying that this tool provides per-item verdicts rather than the principle library.

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 says 'Use this instead of evaluate_design when you need per-item content verdicts', giving an explicit alternative and a specific condition. It also notes the tool is 'Pure offline — no network run or browser', but it does not enumerate scenarios where the tool should NOT be used beyond that single distinction.

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