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

Beyond the readOnlyHint annotation, the description details privacy (never stored), return format (plain-text report with line/column, context, reason for AI tells), an error condition (>100,000 characters), and lack of filesystem access. This adds rich behavioral context beyond the structured 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 compact yet information-dense, with the core purpose front-loaded. Each sentence adds value: behavior, privacy, return details, limits, alternatives, and tool relationship. No words are wasted.

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 absence of an output schema, the description fully explains return format and error behavior. It also covers side effects (none), scope (hosted server, no filesystem), and alternative tools. This is complete for the tool's complexity and context.

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% so baseline is 3, but the description adds a meaningful constraint not present in the schema: texts over 100,000 characters return an error. This clarifies the text parameter's limits. It also reinforces the config's purpose and format's effect without redundancy.

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 a specific verb ('Analyze text for writing style issues') and enumerates the exact issue types (weasel words, passive voice, etc.), distinguishing it from sibling tools. It also explicitly contrasts with fix_duplicates by noting this tool only reports issues.

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?

It gives clear usage context: read-only, stateless, works on in-memory text, and explicitly points to fix_duplicates for automatic removal and to a separate check_file tool for local files. This provides direct alternatives and exclusion guidance.

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