cargar_documento

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

With no annotations, the description carries the full burden. It usefully discloses input modes and a returning behavior ('Devuelve el comienzo y qué hacer después según el tipo'), plus the faithful-transcription expectation. It does not state whether an existing document is overwritten, whether tipo drives different storage, or any auth/permission constraints for this write operation.

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?

Three sentences, front-loaded with the core purpose and then the simplest workflow, with no filler. Each sentence contributes (purpose, input method, return), though it could be tightened slightly and would be more useful if it spent one clause differentiating siblings.

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 write tool with two enums and no output schema, the description adequately covers the primary workflow and states what is returned. The gaps are the unexplained rama parameter and any behavior on repeated saves, so an agent can invoke it but not fully predict the outcome.

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 40% (only ruta and texto are documented), so the description must compensate. It adds meaning for texto ('transcripción fiel') and ruta (file on the computer's PDF/.txt/.md), and its list of document types roughly maps to the tipo enum. But rama (civil/procesal) and titulo semantics are left entirely unexplained in both schema and description.

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: 'Guarda un documento de SU examen', enumerating the document kinds (cedulario, temario, reglamento, examen anterior, pauta) and the persistence scope ('para usarlo en todas las sesiones'). The purpose is clear, but the description never distinguishes this tool from closely named siblings like guardar_cedulario, guardar_material, or agregar_manual, so an agent must still reason about which save-tool applies.

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 gives practical usage guidance on the two accepted input paths ('el estudiante adjunta el archivo... tú lo lees y lo guardas con texto' vs. 'También acepta ruta'), which is genuinely helpful. However, it offers no when-to-use / when-not-to-use guidance relative to the many sibling save tools, leaving the selection question implied.

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