pbi_plan_audit_fixes

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

With no annotations provided, the description carries the full burden. It discloses a key behavioral trait: the tool writes nothing (safe, non-destructive). It also states that it returns the exact actions that would be applied with their reasons. It does not cover other traits like authentication or error behavior, but the core safety aspect is clearly communicated.

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 concise, using three short sentences to convey purpose, safety, and parameter usage. It front-loads the most important information (plans fixes, writes nothing) and contains no fluff or repetition.

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?

Given the tool has a moderate complexity, an output schema, and no annotations, the description covers the essential points: what it does, that it doesn't modify, that rules are required, and that objects narrows. It could mention the source of valid rule IDs (e.g., from audit results or pbi_list_audit_rules), but the output schema already documents the return format, so the description is sufficiently complete for an agent to use it correctly.

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?

The schema has 0% description coverage, so the description must compensate. It explains that `rules` must be explicitly indicated (no implicit 'fix all') and that `objects` narrows to visual/page IDs. This adds meaningful semantic context beyond the schema's bare type definitions, though it does not specify where to obtain valid rule IDs.

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's function: it plans corrections for specific rules ('Planifica correcciones para reglas CONCRETAS') and explicitly says it does not write anything ('No escribe nada'). This distinguishes it from the sibling tool pbi_apply_audit_fixes and clearly implies a planning/preview verb+resource.

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 clear usage context: there is no 'fix everything'–the `rules` parameter must be explicitly provided, and `objects` narrows the scope further. It implies this tool is for planning before applying, but it does not explicitly name alternative tools or state when to use it vs. them.

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