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

No annotations exist, so the description carries the full burden and does it well: it discloses the return payload (score, per-criterion breakdown, three-model divergence, DOI eligibility), the authentication requirement (API key), language behavior (reads any language, answers in the text's language), a calibration caveat across languages, and two scope disclaimers (not peer review, not accreditation).

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 the core action and the return contract, and most sentences earn their place (exclusions, disclaimers, language caveat). It drifts slightly toward prose in the language-calibration and Portuguese-trigger sentences, which are useful but loosely attached.

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 supplies the return values, the authentication requirement, the idempotency hook, and the scope boundaries an agent needs before calling. It stops short of describing errors, latency, or where get_criteria must be consulted first, which for a 5-parameter tool leaves a small gap.

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%, so the schema already explains text, title, work_type, evaluation_id and academic_level. The description adds only indirect meaning — the excluded document classes constrain which work_type values are valid — without naming any parameter, so baseline 3 applies.

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 verb+resource are specific: score a text against published academic criteria, with concrete input types (paper, case report, thesis chapter, teaching material) and a stated output (0–100 score). It never names the sibling screen_text, so an agent cannot tell from this text alone how scoring differs from screening.

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 (user wants to know how strong a work is, or wants a reviewable score before submitting) and explicit when-not-to-use (recipes, operational legal documents, workout plans, how-to instructions). Alternatives such as screen_text or get_criteria are not referenced as routing options.

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