Skip to main content
Glama

Guardar las notas en Educa

educa_save_grades
Destructive

Saves entered grades in Educa Navarra by pressing the gradebook Save button after explicit teacher confirmation, then captures before/after screenshots and returns Educa's message.

Instructions

Pulsa el botón Guardar/Grabar de la pantalla de calificaciones para que Educa registre las notas escritas con educa_fill_grades. Hace una captura antes y otra después y devuelve el mensaje que muestre Educa.

IMPORTANTE: llama solo cuando el profesor haya dicho expresamente que guarde, y pasa confirm=true. No cierra ni firma la evaluación (eso debe hacerlo el profesor a mano).

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": {
      "confirm": "<confirm>"
    },
    "name": "educa_save_grades"
  }
}

Input Schema

NameRequiredDescriptionDefault
confirmYesDebe ser true: confirma que el profesor ha autorizado guardar

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.7/5.0
Behavior4/5

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

The description adds real behavior beyond the annotations: it captures a screenshot before and after, returns the message Educa displays, and deliberately stops short of closing or signing the evaluation. What it does not disclose is the practical consequence of destructiveHint=true — whether existing saved grades can be overwritten and whether the action can be undone.

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?

Two short paragraphs, action first, safety constraint second under an explicit IMPORTANTE marker. Every sentence carries either the action, the evidence it produces, or a boundary, with no filler.

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

Completeness5/5

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

For a one-parameter, no-output-schema tool this is complete: trigger condition, required argument, what is captured around the action, what is returned, and what is intentionally left to the human. Nothing needed to invoke or avoid invoking it is missing.

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?

With a single parameter at 100% schema coverage the schema already constrains confirm to the constant true. The description nonetheless adds the intent behind it — that the value records the teacher's explicit authorization — which is the meaningful semantic an agent needs to avoid calling it unprompted.

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

Purpose5/5

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

States a concrete verb and resource (press the Save/Record button on the grades screen so Educa registers the grades written by educa_fill_grades), which cleanly separates it from the sibling that only fills grades in. An agent can tell the difference between writing into the form and committing it without opening either schema.

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

Usage Guidelines5/5

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

Explicitly gives the precondition ('llama solo cuando el profesor haya dicho expresamente que guarde'), the required argument (confirm=true), and an explicit exclusion: it does not close or sign the evaluation, which the teacher must do manually. The alternative (educa_fill_grades) is named as the producer of the grades this tool commits.

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