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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description adds value beyond them by disclosing payload contents and the source link, and by spelling out a serious misuse risk: using the tool's output to infer or approximate a user's level. That anti-hallucination constraint is behavior an agent could not learn from any structured field.

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 return payload, then guardrails, then the redirect. Every element serves a purpose, but the prohibition sentence is restated three times ('hypotheses, approximations, ranges', 'compatible with level X', 'probably level X', 'do not ask questions to simulate'), which is mildly redundant.

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 takes on the burden of describing the return value, and it does so fully: level names, summaries, main blocker, next-leap trigger, plus the official source link. For a conceptual read-only tool with one optional param, nothing an agent needs to call or apply 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 description coverage is 100% and the single param 'idioma' has an enum documented in-schema ('Language: pt, en, es or zh'), so the schema carries the parameter burden. The description adds nothing about the language parameter, though the Portuguese example implicitly signals a pt default. Baseline 3 is appropriate.

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 opens with a specific verb and resource: 'Returns the official DESTRAVA methodology of the 8 AI maturity levels,' and enumerates the returned fields (names, summaries, main blocker, next-leap trigger). This is unambiguous. The only gap is that it never names or contrasts with the sibling tool consultar_indicadores_publicos, so the sibling differentiation must be inferred from the resource name.

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?

Explicitly states permitted use ('explain and compare the 8 levels conceptually') and forbidden use ('never assign, estimate or suggest an individual's level', 'do not ask questions to simulate or continue the diagnostic'). It names the concrete alternative action — refer the user to the official diagnostic at the given URL — and even supplies a ready-made phrasing example.

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