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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds genuinely new behavior: no protocol error is ever raised, errors come back as {"error": ...} with fix guidance, and retry-after-correction is safe. It also discloses the cost model ('FREE') and what the score means and does not mean.

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?

Front-loaded with purpose and cost, then evidence model, then examples, then exclusions. The embedded request/response sketches are the bulkiest part and partially duplicate the output schema, but nothing is truly 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?

For a one-parameter read-only tool with an output schema, this covers purpose, evidence format, score interpretation, error contract, retry safety, and sibling routing. An agent has everything needed to select and invoke it 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%, so the single text parameter is already documented; the description goes further by showing a concrete input shape ({"text": "<draft>"}) and the shape of the response. It adds modest value over the schema rather than new semantic detail about the parameter.

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?

States a specific verb+resource ('Scan a draft for the measurable tells of AI-generated prose') and immediately enumerates what it detects: stock phrases, structural reflexes, sentence rhythm, em-dash overuse, hedging. It also names the sibling tools it is not (burstiness_report, humanize_plan), so an agent can distinguish it without opening schemas.

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?

Explicit when-to-use ('first read on whether a draft carries machine-writing signals') and explicit when-not, naming both alternatives and their distinct purposes. It also constrains scope ethically ('must not be used to accuse a person'), which is a real usage boundary an agent needs.

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