pbi_audit_model

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds valuable context by stating that each finding includes evidence and that 'ninguna heuristica se presenta como certeza' (no heuristic is presented as certainty), which clarifies the epistemic nature of results. It does not mention side effects or permissions, but for an audit tool this is a meaningful disclosure.

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 efficiently structured: a one-sentence purpose, a sentence detailing finding fields, a caveat about heuristics, and two parameter clarifications. Every sentence adds value with no redundancy or filler.

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?

The description covers the output structure (rule, severity, object, evidence, recommendation, auto_fix_available), explains key parameters, and discloses the tool's epistemic limitations. It misses the `source` parameter, which is a gap, but the existence of an output schema reduces the need to describe return values in detail.

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?

Since schema description coverage is 0%, the description must compensate. It explains that `rules` is a subset from pbi_list_audit_rules and enumerates possible values for `min_severity` (info | warning | error). However, it completely omits the `source` parameter, leaving it undefined in both schema and description.

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 'Audita el modelo semantico' (audit the semantic model) with a specific verb and resource, and further specifies 'reglas de identificador estable' (stable identifier rules). It doesn't explicitly differentiate from sibling audit tools like pbi_audit_project or pbi_analyze_model_quality, so it falls short of full distinction.

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 implies usage for auditing semantic models with a subset of rules and a severity threshold, referencing pbi_list_audit_rules for rule selection. However, it provides no explicit guidance on when to choose this tool over overlapping siblings like pbi_audit_project or pbi_analyze_model_quality.

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