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

No annotations, so the description carries the full burden and does substantial work: it discloses the calibrated accuracy (AUROC 0.94, 1.7% false accusations), that output is a probability level and never proof, that text is not stored, and that each call costs $0.0270 via x402. That covers privacy, cost, and interpretation risk. What's missing is latency, rate limits, and behavior on out-of-scope input.

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?

A single dense sentence, front-loaded with the language and method before the caveats and pricing. Every clause carries information (accuracy stats, probabilistic output, no storage, price). Slightly overloaded with parentheticals, but nothing is 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?

With no output schema and no annotations, the description must explain the return, which it does at a high level ('probability level, never proof') along with cost and privacy. It falls short only in not describing the shape of the probability output (scale, thresholds) that an agent would need to act on the result.

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 the parameter already documented as 'Portuguese text, ideally 90+ words' and capped at 8000 chars, so the baseline is 3. The description adds only the PT-PT language constraint, which is real but marginal; it does not explain what happens with non-Portuguese or short input.

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 ('AI-generated text detector') and nails the scope down to European Portuguese (PT-PT) with the named method (Binoculars). An agent can tell immediately this is a detection/classification tool, distinct from siblings like localizar-pt-pt (localization) or chat-gpt-oss (generation).

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?

Usage is implied: it detects AI-generated PT-PT text, and the 'never proof' framing signals it's advisory evidence rather than a verdict. But it never says when NOT to use it (e.g., non-Portuguese input, very short texts despite the 90+ word hint living only in the schema) and names no alternative sibling. Adequate, with clear gaps.

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