Skip to main content
Glama

Editar curso

update_course

Edits selected fields of an existing editable Chispa course, changing only the details provided; confirm publication or visibility changes with the user before applying them.

Instructions

[Equipo del aula] Cambia los datos de un curso que puedes editar. Solo se modifica lo que envíes. Confirma con la persona antes de publicar o cambiar la visibilidad.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "classroom_id": "<classroom_id>",
      "course_id": "<course_id>"
    },
    "name": "update_course"
  }
}

Input Schema

NameRequiredDescriptionDefault
slugNoDirección del curso (minúsculas, números y guiones)
titleNoTítulo
audienceNoA quién va dirigido (omítelo para no cambiarlo; "" lo borra)
positionNo
subtitleNoSubtítulo (omítelo para no cambiarlo; "" lo borra)
course_idYesCurso
objectiveNoObjetivo (omítelo para no cambiarlo; "" lo borra)
publishedNotrue publica, false pasa a borrador
difficultyNoNivel; «ninguno» lo quita
visibilityNo
descriptionNoDescripción (omítelo para no cambiarlo; "" lo borra)
classroom_idYesAula

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations only say readOnly=false, destructive=false, openWorld=false. The description goes beyond them by disclosing that the operation is a merge/patch (only submitted fields are touched, others preserved), that only courses you have edit rights over are affected, and that publishing or visibility changes require human confirmation first. It does not state what is returned or how permission failures surface.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, no filler: scope first, mutation semantics second, the safety caveat last. Each sentence carries distinct information an agent needs before calling.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 12 parameters, two undocumented enums and no output schema, the description covers mutation semantics and the confirmation rule well but leaves gaps: the `visibility` enum values are unexplained anywhere, and the relationship between this tool's `published` flag and the set_published sibling is unresolved. Adequate but not fully self-sufficient for a 12-parameter mutation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 83%, so most field meanings are already documented, including the omit-vs-empty-string convention. The description nonetheless adds a global semantic rule that applies across all ten optional parameters – unspecified fields are left untouched – and flags the two fields (published, visibility) that deserve extra care. It adds nothing field-specific for `visibility`, whose enum has no schema description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Cambia los datos de un curso que puedes editar" gives a specific verb (cambia/update) and resource (curso), plus a scope qualifier about which courses are editable. An agent can separate it from create_course, delete_course, update_module or update_lesson without reading schemas, though no sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Solo se modifica lo que envíes" establishes the partial-update contract, and "Confirma con la persona antes de publicar o cambiar la visibilidad" adds a clear precondition for the two risky fields. However, it never routes the agent away from alternatives – notably the sibling set_published, which overlaps with this tool's `published` parameter – so the when-to-use-this-vs-that question stays unanswered.

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