pbi_preview_spec_html

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

With no meaningful annotations (all hints false), the description carries the burden. It explicitly discloses the key non-destructive behavior ('sin escribir nada al .pbip') and states the output is an HTML file path. It does not detail file cleanup or potential side effects of creating the HTML file, but the main behavioral trait is transparent.

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 two compact sentences with the key information front-loaded. Every phrase earns its place: the action, the non-destructive guarantee, the spec shape, and the output path. There is no wasted text.

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 is moderately complex (spec-driven HTML generation), and the output schema exists, so return values do not need elaboration. The description provides a sufficient input template and usage context. It could add more detail about required vs optional spec fields, but the provided structure is adequate for initial use.

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 only defines an opaque 'spec' object with additionalProperties and 0% description coverage. The description compensates by providing a concrete structure: {page_name, canvas?, layout?, visuals:[{type,title,fields,position?}]}. This gives meaningful guidance beyond the bare schema, though individual fields are not explained in depth.

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 generates an HTML mockup of a proposed page ('Genera una MAQUETA HTML de una hoja propuesta') and explicitly distinguishes it from write operations by adding 'sin escribir nada al .pbip'. The verb, resource, and output are all specific, and it differentiates from siblings like pbi_create_page_from_spec and pbi_apply_page_spec.

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 implies when to use it: to review a proposed page design in the browser before committing anything to the .pbip file. It provides a clear workflow via the returned HTML path, though it does not explicitly name alternatives or state exclusions, so it falls short of a 5.

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