exportar

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

With no annotations, the description carries the full burden and does so well: it discloses where output lands, that existing destinations are never overwritten but suffixed _2/_3..., that PNG/JPEG and HTML produce folders rather than files, that GIF requires ffmpeg, and that video is 1080p with transitions. These are exactly the side-effect and dependency facts an agent needs before invoking.

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?

Two compact sentences that front-load the format list, then the destination behavior. The enum enumeration is long but earns its place as the tool's core capability; a reader can stop after the first clause and still call it correctly.

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 5-parameter, annotation-free, mutation-producing tool the description covers formats, side effects, collision handling, and external dependencies. The remaining gap is the return value (e.g., resulting file path) which, absent an output schema, the description could have stated.

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 80%, so the baseline is 3; the description goes beyond it by clarifying that the same destino argument means a file for pdf/pptx but a folder for png/jpeg/html, and that image export yields one file per visible slide. It does not touch etapas or con_notas, but the schema already documents those.

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?

Opens with a precise verb plus resource ("Exporta la presentación") and immediately enumerates every supported target format, which matches the formato enum exactly. An agent can distinguish this from siblings like guardar or presentar without opening the schema.

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?

Conveys useful operating context (default output folder, non-destructive naming) but never states when to reach for this tool versus alternatives such as guardar (save) or presentar (run the show). The choice is inferable from the name, but no explicit routing or preconditions are given.

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