audit_content

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, indicating safety. The description adds value by specifying 'Pure offline — no network or browser' and detailing the deterministic heuristics. It does not contradict 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 a single paragraph dense with information, front-loading the purpose and then detailing heuristics and output. It is concise but could be slightly more structured (e.g., breaking heuristics into a list). Minimal waste.

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?

Despite no output schema, the description thoroughly explains the return format: per-item verdict with matched principle ids, issues, rewrite suggestion, and an aggregate summary. It lists heuristics for each content type, making the tool fully understandable.

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%, with detailed descriptions in the schema (e.g., for 'type' it says 'Content type — selects which heuristics apply'). The tool description adds context on item types and heuristics but does not significantly enhance parameter meanings 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 clearly states the tool evaluates content items against UX-writing principles and heuristics, listing specific item types (headings, prose, CTAs, etc.) and the output per-item verdict. It also explicitly distinguishes itself from the sibling evaluate_design by contrasting their outputs.

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 provides explicit guidance on when to use this tool ('when you need per-item content verdicts') and when not to ('rather than the principle library'), naming the alternative evaluate_design. This helps the agent decide correctly.

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