tabla_estructura

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

With no annotations at all, the description still discloses substantive behavior: the style/format is reapplied as a side effect, merging concatenates cell texts with a tab in Keynote, sorting leaves the header on top, and added rows/columns preserve width. It stops short of warning that quitar_fila/quitar_columna destroys cell data or describing what is returned, which are the remaining gaps for a mutation tool carrying the full disclosure burden.

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 core purpose is front-loaded and each parenthetical adds real operational detail rather than filler. It is a single dense sentence with nested clauses, which is slightly harder to scan than a short bulleted breakdown of the seven actions, but nothing is wasted.

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?

For a 9-parameter mutation tool with no annotations and no output schema, the description covers all seven actions and their key side effects but leaves index semantics, sort direction, quantity handling, and data-loss on removal unstated. Adequate to invoke it, not fully sufficient to invoke it confidently.

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 only 22%, so the description has to compensate, and it partially does: it clarifies `rango` with the "A1:B1" format, that `columna` is the sort key, and that additions go at the end. It says nothing about `descendente` (sort direction), `cantidad`, `tabla` (default 1), or whether `fila`/`columna` are 1-based, leaving several parameters undocumented in both places.

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 names a specific verb and resource ("Cambia la estructura de una tabla") and then enumerates exactly the seven structural operations that match the `accion` enum, so an agent can tell it apart from content-level siblings like editar_celdas or tabla. It never names an alternative tool explicitly, which keeps it at 4 rather than 5.

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?

Usage is implied by mapping each action to a situation (fusionar/separar a range, ordenar by a column, agregar al final, quitar), and one real guideline is given (merge empty cells with a filled one because Keynote joins texts with a tab). There is no explicit when-not-to-use guidance or reference to editar_celdas/tabla as alternatives, so the agent must infer the boundary.

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