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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds context about LGPD compliance, that data is not confidential, that clients are data controllers, and that prepaid credits are used. It does not disclose rate limits, failure modes, or what happens on invalid credentials. Credits the annotations with reducing the need for behavioral disclosure, but the LGPD note is a differentiator.

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 a single run-on sentence with embedded legal/pricing information, which fronts the core purpose but meanders into LGPD details. It is not excessively long, but punctuation issues (e.g., missing space after parenthesis, awkward clause 'não é dado sigiloso.') make it slightly less readable. No bullet points or structured formatting.

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 7 parameters, no output schema, and 0% schema coverage, the description needed to cover parameter formats, return values, and expected behavior. It only addresses LGPD and payment, leaving critical operational details undocumented. The tool's moderate complexity (string parameters only, no nested objects) means a more thorough description could have covered these gaps.

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?

Params are 7 with 0% schema description coverage, and the description provides zero parameter explanations. Parameter names (uc, uf, mes_ano, login_cpf, login_cnpj, login_senha, acesso_imobiliaria) are visible but formats (e.g., date format 'MM/YYYY' for mes_ano, whether uc is a string of digits) are undocumented. The description's LGPD focus does not compensate for the lack of parameter-level guidance.

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 clearly states the tool performs 'Download + OCR' for 'Neoenergia (Elektro)' utility bills with 'consulta em fonte oficial'. This is specific about the resource (Neoenergia) and action (download/OCR/consult), distinguishing it from generic sibling tools. No explicit verb like 'returns' but 'consulta' implies retrieval. Minor ambiguity: 'Download + OCR' is a fragment, not a full sentence.

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 description provides context about when to use this tool: for Neoenergia utility bill queries, hosted on the platform without platform credentials, with pay-per-query pricing. However, it does not explicitly state when NOT to use it or name alternative tools. No comparisons to siblings or other Neoenergia-specific tools are provided.

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