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

Annotations already set readOnlyHint, idempotentHint, and destructiveHint. The description adds significant value by detailing error handling ('never raises a protocol error — it returns {"error": ...}'), idempotency safety for retries, and the exact response structure. 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 a single well-structured paragraph that front-loads the purpose, follows with a usage example, then usage guidelines, and ends with error behavior. Every sentence adds value; no wasted words.

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 only one input parameter, the description fully explains the return structure (reads_human_score, metrics, evidence, note) and error handling. The presence of an output schema is supplemented by clear documentation. The tool scope is simple and completely covered.

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?

Only one parameter (text) with 100% schema coverage. The description adds meaning beyond the schema by providing a typical input example ('{"text": "<draft>"}') and clarifying input requirements ('at least one full sentence of plain text'). This aids correct invocation beyond the schema alone.

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 uses a specific verb ('Scan') and resource ('draft') and clearly states the outcome ('measurable tells of AI-generated prose'). It distinguishes from siblings by explicitly naming alternative tools (burstiness_report, humanize_plan) and what those tools cover.

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 usage context: 'Use for a first read on whether a draft carries machine-writing signals.' Also states when not to use: 'must not be used to accuse a person of anything' and lists alternative tools, satisfying the when/when-not/alternatives criteria.

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