Validate Citations

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

With no annotations, the description carries the full burden and does well: 'auditoria' frames it as a diagnostic, and it discloses the three source formats (LaTeX, Markdown, Typst) and the three defect classes it reports. It stops short of stating that no files are modified or how it behaves when no .bib is found, so the safety profile is inferred rather than declared.

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 verb, then four tight bullets that each add non-redundant information. No filler; the only minor cost is that it spends its length on output scope while spending none on the inputs.

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, so return values need not be explained, and the defect taxonomy is well covered. But for a two-parameter tool with zero schema documentation, the description should say what project_path points at and when bib_path must be supplied; that gap is what holds this to adequate.

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 0% and neither parameter is explained anywhere in the description. The phrase 'entre o texto e as referências' hints that one path is the project and one is the bibliography, but the meaning of bib_path's null default (auto-discovery? skip the orphan check?) is left entirely unresolved — a real risk of misuse.

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 and resource — a cross-audit between the document text and its references — then enumerates exactly what it checks (orphan citations, uncited .bib entries, uppercase surnames violating NBR 10520:2023). That enumeration distinguishes it from siblings like clean_bibtex_file (which repairs) and format_citation (which formats a single citation).

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 by the listed checks: an agent can infer it should call this before submission to find unresolved or uncited references. However, there is no explicit when-to-use statement, no mention of prerequisites (must a .bib already exist?), and no guidance on when to pass bib_path versus relying on discovery.

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