Audit Illustrations And Tables

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

With no annotations, the description carries the full burden; the verbs (Detecta, Aponta, Verifica, Diagnostica) clearly signal a read-only inspection, and it discloses that it touches the physical filesystem to verify image existence. It does not state whether any files are modified, permission requirements, or how results are ranked, though an output schema exists to cover structure.

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 purpose sentence followed by four tight bullets, each earning its place with a concrete rule ID. The only friction is the Portuguese body against an English tool name, a minor consistency cost.

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?

For a one-parameter diagnostic with an output schema handling return shape, the definition covers what is audited and by which rule. Remaining gap is mostly path expectations for the single input.

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% on a single parameter, so the schema supplies no meaning; the description only implies project_path is the project root whose referenced images are checked. It does not define expected form (relative vs absolute, must the project follow a scaffolded layout).

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 (audit) and precise resources (figures, tables, quadros) plus the governing standards (NBR 14724 item 5.8, IBGE 1993). It does not explicitly contrast with siblings format_figure/format_table, but the enumerated checks make the auditing 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?

Usage is implied by the diagnostic checklist (missing textual callouts, missing 'Fonte:', broken image paths, out-of-sequence numbering) rather than stated as when-to-run. No exclusion tells the agent to prefer format_table or format_figure for fixing rather than auditing issues.

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