Validate Qa

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

With no annotations, the description carries the full burden and does disclose real behavior: severity semantics ("length-only checks emit WARN, never CRITICAL"), the non-destructive editorial stance ("no automatic QA->Cloze conversion"), and the return payload contents. It does not state read-only status, permissions, or whether validation mutates anything, which is a moderate gap for a no-annotation tool.

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 and dense: purpose first, then checks, then return shape, with parenthetical caveats instead of extra sentences. Some code strings (QA.YESNO, QA.MC_EMBED, QA.NUMBER_UNIT) are listed without glosses, which reads as internal shorthand rather than agent-facing prose.

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?

An output schema exists and the description still names information_profile, candidate_items, evidence, and the editorial checklist, so return semantics are covered. For a validator with zero annotations and zero parameter descriptions, what remains thin is the meaning of individual check codes and the unmentioned `row` parameter, but nothing essential to invoking it correctly is missing.

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 0%, so the description must compensate; it partially does by glossing the pair as "stem + answer" and clarifying that stem context length is not extra recall. However, the third parameter `row` (integer, default 0) is never mentioned, and the description does not bind its wording explicitly to the `enunciado`/`resposta` field names.

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?

"Validate a QA pair (stem + answer)" gives a specific verb plus resource and even disambiguates the two required inputs. The rule "no automatic QA->Cloze conversion" implicitly draws the boundary with the cloze validator, and the enumerated check codes make the QA-only scope unmistakable.

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 usage is implied by the resource (a QA pair with stem and answer) but there is no explicit "use this when / use X instead" statement, and the many sibling validators (validate_cloze, validate_batch, validate_crossrefs) are never routed against. The cardinality rule ("≥3 items → review unit, split independent recalls or move optional details to notes") is editorial guidance rather than tool-selection guidance.

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