pbi_repair_broken_references

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

With no annotations, the description carries the behavioral disclosure burden. It clearly indicates that without mapping the tool is diagnostic, and with mapping it performs a write operation, validating the destination against the model before writing. This discloses the mutation and safety behavior, though it does not mention the effect of the dry_run parameter on whether writes occur.

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 only two sentences, front-loaded with the purpose, followed by a concise explanation of the two modes. Every sentence adds value, and the example is embedded naturally without verbosity.

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 core functionality well: the dual diagnostic/repair mode, validation behavior, and mapping format. With an output schema present, return values need not be explained. However, the dry_run and request_id parameters are left unexplained, and the description does not mention prerequisites like an open project or model, which are relevant for a repair operation.

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 description adds meaningful context for the mapping parameter with a concrete JSON example: 'Pasa {"Tabla[Viejo]": "Tabla[Nuevo]"} para repararlas'. However, it does not explain dry_run or request_id, and schema description coverage is 0%, so these parameters remain opaque. The example helps but does not fully compensate for the lack of parameter explanations.

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: 'Detecta referencias rotas en los visuales y las repara' (detects and repairs broken references in visuals), with a specific verb and resource. This distinguishes it from sibling tools like pbi_replace_visual_field, which focuses on field replacement, and pbi_apply_audit_fixes, which is broader.

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 explicit usage modes: without 'mapping' it only diagnoses, and with 'mapping' it repairs. It even warns that guessing the target field is not a decision to make alone, implying that mapping should be provided for repairs. However, it does not compare directly to alternative tools or state when not to use this tool.

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