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

Beyond annotations that already mark it read-only and non-destructive, the description discloses meaningful traits: text is not stored, detectors can make mistakes, results are likelihoods rather than proof, and non-English languages use language-specific detectors. It also notes that results are returned for the whole text and for each part.

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 four sentences and front-loads the core purpose. Each sentence earns its place by covering scope, language support, return granularity, accuracy caveats, and privacy.

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?

With no output schema, the description must explain what is returned, and it does so by stating that an AI likelihood is returned for the whole text and each part. Given one parameter and no siblings, the privacy note and error caveat make the definition sufficiently complete for correct use.

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?

There is a single required text parameter with 100% schema description coverage. The description repeats the 50–2,000 word range and language list already present in the schema, but adds no additional syntax, formatting, or input-preparation guidance beyond that.

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 states a specific action (checks whether text looks AI-written), the resource (text), the applicable word range, and supported languages. It is immediately clear what the tool does, and there are no sibling tools requiring differentiation.

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 purpose makes the intended use case clear: detecting AI-authored text. It also adds a useful caveat that results are likelihoods, not proof, and documents language and word-count limits. It stops short of explicitly saying when not to use the tool, but no alternatives exist in the sibling list.

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