pbi_generate_page_spec

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

With no annotations, the description must disclose behavioral traits. It states that the output is an editable draft spec and should be validated, implying it is non-destructive and not directly applied. However, it does not explicitly mention side effects, permissions, or what happens to the generated spec beyond returning it. Some behavioral context is provided, but not exhaustive.

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 and well-structured: a one-sentence purpose, a bullet list of parameter meanings, and a closing instruction. It is front-loaded with the core purpose and uses minimal words to convey the workflow.

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 tool has an output schema, so return values need not be explained. The description gives enough context for an agent to know this generates a draft spec that needs validation, and the parameter list covers the key customization options. However, it could more explicitly differentiate from other page-generation siblings and mention the page_name requirement, though overall it is sufficient for a low-risk generation tool.

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 explains the meanings of `preset`, `measures`, and `category`, which are the domain-specific parameters. However, the required `page_name` and `width`/`height` are not explained, though their names and defaults make them somewhat self-evident. Since schema coverage is 0%, the description partially compensates but leaves gaps.

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: 'Genera un borrador de spec a partir de un preset y unos campos' (generates a draft spec from a preset and fields). It also enumerates available presets, making the purpose specific. However, it does not explicitly distinguish from sibling tools like pbi_build_executive_page or pbi_generate_report_page, though the focus on a draft/editable spec implies a unique role.

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 a clear workflow: generate an editable spec, review it, and pass it through pbi_validate_page_spec. This gives when-to-use context. It does not explicitly mention alternatives or when not to use, but the validation step implies the intended lifecycle.

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