pbi_plan_audit_fixes

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

With no annotations, the description compensates by disclosing the non-destructive nature ('No escribe nada'), the requirement for explicit rules, the scoping effect of objects, and the nature of the return value (exact actions with reasons). It doesn't cover edge cases like invalid rules or prerequisites, but the primary behavioral traits are covered.

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 compact and front-loaded with the main purpose, followed by key constraints and return behavior. Each sentence adds meaningful information without redundancy or fluff.

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's moderate complexity (two parameters, output schema available), the description adequately covers what the tool does, its non-writing behavior, required inputs, and expected output. It is complete enough for an agent to decide when and how to use it.

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%, yet the description provides essential meaning for both parameters: `rules` must be explicitly provided because there is no 'fix everything', and `objects` further narrows the scope to visual or page IDs. This goes beyond the raw schema but does not detail string formats or rule name conventions.

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 that the tool 'plans fixes for specific rules' and explicitly says 'it doesn't write anything,' which distinguishes it from applying fixes. It identifies the resource (audit fixes) and scopes its purpose to concrete rules rather than a broad 'fix all' action.

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?

It explicitly explains that 'there is no fix everything' and that `rules` must be specified, while `objects` is optional and narrows the scope to visual or page IDs. Although it doesn't name alternative tools, the statement that it does not write anything clearly implies a planning-only role versus applying changes.

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