ver_diapositiva

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

readOnlyHint=true already tells the agent this is a safe read, and the description usefully adds that the output is Keynote's own rendering (a fidelity claim an agent could not infer from schema or annotations). It says nothing about cost, latency, whether the document must be open, or how the image is returned, which limits it to a 3.

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?

One front-loaded sentence with the resource and the fidelity qualifier first, then the purpose. No filler, though the trailing purpose clause overlaps slightly with the image claim it already made.

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 simple read-only render tool with annotations covering safety and no output schema, the description is nearly sufficient: it names the return format and the fidelity guarantee. The only real omission is the undocumented ancho_max sizing behavior, which matters because it governs the returned image.

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 coverage is 67%: documento and diapositiva are well documented in the schema, but ancho_max carries no description anywhere and the description never mentions that output size is controllable. The description adds no parameter meaning beyond the schema, so it sits at the moderate-coverage baseline rather than compensating for the 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?

States a specific verb and resource ('Devuelve la imagen PNG de una diapositiva') and adds a meaningful qualifier ('tal como la dibuja Keynote'), so the agent knows this is a rendered preview, not a data read. It does not name or contrast with the nearest sibling (exportar), which keeps it from a 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?

'para revisar el resultado' implies the use case — visually verifying a slide after edits — but there is no explicit when-to-use/when-not guidance and no mention of when to prefer exportar or revisar_presentacion instead. Usage is inferable but not stated.

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