pbi_open_in_desktop

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

With annotations all false, the description carries the full burden. It discloses critical behaviors: waits for the local engine to appear and stabilize, identifies the correct instance via dynamic port, uses select=true to set active model, reuses open sessions with reuse_open, and 'Nunca cierra una ventana del usuario.' It also warns about the lack of data in newly opened .pbip files. This is exceptional transparency beyond annotations.

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 structured with a clear opening action, rationale, technical details, and a caution. Every sentence adds value: the 'Cierra el ciclo de trabajo' explains purpose, the engine-wait details explain mechanism, the reuse sentence clarifies idempotent behavior, and the final warning prevents misuse. No redundant or wasted words.

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 complexity (dynamic port, session reuse, no-data caveat), the description covers essential workflow aspects. It omits details about return values, but an output schema exists. It also does not mention the timeout parameter's specific behavior, but the overall context is sufficiently complete for an agent to use the tool correctly.

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%, so the description must compensate. It explains 'select' ('con select=true, lo deja como modelo activo') and 'reuse_open' ('Si el archivo ya estaba abierto se reutiliza esa sesion y no se toca nada'), but does not explain 'timeout' or 'path' beyond the obvious. It adds value for some parameters but not all, leaving 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 specific action: 'Abre un .pbip o .pbix en Power BI Desktop y espera a que sirva el modelo.' It distinguishes from siblings like pbi_open_and_refresh by explicitly noting it does not refresh and directing to pbi_refresh_model for value checks. Also clarifies the use case of verifying a TMDL loads.

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 explains when to use this tool: 'despues de editar un proyecto, esto permite comprobar que ABRE de verdad y consultar sus medidas.' It also provides an exclusion: 'Ojo: un .pbip recien abierto trae el modelo SIN DATOS. Refresca despues con pbi_refresh_model si vas a comprobar valores.' This gives clear context, though it does not explicitly name alternative tools for different scenarios.

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