Skip to main content
Glama

Pulsar un enlace o botón

educa_click

Click a visible link, tab, or button by text or CSS selector to navigate to gradebook screens in Educa Navarra; unsafe actions like closing, signing, blocking, deleting, or publishing are refused.

Instructions

Pulsa un enlace, pestaña o botón visible de Educa por su texto (p. ej. "Evaluación", "Calificaciones", "1º ESO A") o por selector CSS. Sirve para navegar hasta la pantalla de notas. Por seguridad se niega a pulsar cualquier cosa que suene a cerrar, firmar, bloquear, borrar o publicar; para guardar notas usa educa_save_grades.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "educa_click"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNoTexto visible del elemento
exactNoExigir coincidencia exacta del texto
selectorNoSelector CSS, si el texto no basta

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?

Annotations declare readOnlyHint=false and destructiveHint=false, and the description adds real behavioral context beyond them: a safety filter that refuses destructive-sounding targets, which is exactly the kind of guardrail an agent needs before invoking. It does not describe failure behavior (element not found, ambiguous matches, timeout), which is the main remaining gap.

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 tight sentences, front-loaded with the action and its locator, then the purpose, then the safety boundary and the alternative. Every clause carries information; no filler.

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

Completeness4/5

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

For a click tool with no output schema and fully documented parameters, the definition covers purpose, locators, safety refusals and the sibling escape hatch. It stops short of describing what a successful click returns or how ambiguous/no-match cases are reported, which would round it out.

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

Parameters5/5

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

Schema coverage is 100%, so the baseline is 3, and the description earns more by giving concrete text examples ("Evaluación", "Calificaciones", "1º ESO A") and by stating precedence: selector is the fallback "si el texto no basta", which the schema does not convey.

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 specific verb and resource ("Pulsa un enlace, pestaña o botón visible de Educa") plus the two locating mechanisms (visible text or CSS selector) and the goal ("navegar hasta la pantalla de notas"). It also names the sibling it is not (educa_save_grades), so an agent can separate clicking-to-navigate from saving.

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?

Explicit when-to-use (navigate to the grades screen), explicit when-not (anything that sounds like closing, signing, blocking, deleting or publishing), and an explicit redirect to educa_save_grades for the writing case. Little is left to inference.

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