pbi_replace_visual_field

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

Beyond the annotations (all false, giving no safety profile), the description discloses important behavioral traits: it fails loudly instead of silently doing nothing, and it validates the destination against the model before writing, rejecting with field_not_found if invalid. This adds meaningful context about error handling and validation, though it omits details about reversibility or permissions.

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 well-structured. Each sentence serves a purpose: the first states the core action, the second defines the parameter formats and scope, and the third clarifies validation and error behavior. There is no fluff or redundancy.

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 essential aspects: purpose, parameter format, constraints, and error behavior. It does not explain prerequisites like which model must be open, but the output schema exists (which likely covers return values) and the tool's scope is well-defined. Given the large sibling set, the description adequately distinguishes the tool but could benefit from an explicit usage scenario.

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?

With 0% schema description coverage, the description compensates by explaining the format of old_ref and new_ref ('Tabla[Campo]' or '[Medida]'). The remaining parameters (page, visual_id, request_id) are likely self-explanatory from their names, but the description does not add any semantics for them, so it only partially compensates for the coverage gap.

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 opens with a specific verb and resource: 'Sustituye una referencia de campo dentro de un visual' (replaces a field reference within a visual). It also explains the reference format and explicitly distinguishes itself from other visual operations by stating it works on existing projections and does not create new roles.

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 context by specifying constraints (only works on existing projections, does not create new roles) and error behavior (fails if old_ref is not referenced), but it does not explicitly mention when to use this tool versus alternatives. For example, it doesn't state 'use this for swapping fields, while pbi_set_visual_filter is for filtering'—such guidance is only implied.

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