leer_presentacion

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

Annotations already mark this as readOnlyHint=true, so the safety profile is covered. The description adds valuable behavioral detail beyond annotations by enumerating the returned slide fields and explaining the expanded object-level result when detalle=true.

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 are front-loaded with the main read behavior and then the detalle=true variant. The listing is dense but every enumerated field contributes to understanding the return shape.

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?

There is no output schema, so the description must carry return-value context. It does so for both the default slide-level mode and the detalle=true object-level mode, which is sufficient for an agent to understand what will be returned.

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 75%, with documento, desde and hasta already documented in the schema. The description adds important meaning for the otherwise undocumented detalle parameter and explains that object indices are intended for use with poner_texto.

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: reads a presentation slide by slide, including layout, skipped state, title, body, notes, transition, object counts and texts. It clearly describes the detalle=true variation, but does not explicitly distinguish itself from sibling tools such as ver_diapositiva.

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 gives useful usage context by explaining when detalle=true should be used and by linking returned object indices to poner_texto. It does not state when to prefer this over ver_diapositiva or other presentation-reading siblings.

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