clickedu-mcp

add_tutor_conversation

Records one tutor conversation (interview summary) in a student's file, with participants and Markdown-to-plain-text preview; saves only after confirmation and never notifies participants.

Instructions

Record ONE tutor conversation (an interview summary) in a student's file: 'Comunicació > Converses del tutor > Nova', with a title and a message, and the participants ticked. Only the student's tutor can do this.

The 'Notificar als participants' box is NEVER ticked: nobody is emailed.

text may be Markdown (e.g. a Granola summary): it is converted to plain text, because Clickedu shows the message literally. Headings, paragraphs, line breaks and list items are kept; #, ** and other markers are removed. The preview shows the exact text that will be saved.

participants: who took part, matched against the names or roles on the form ("alumne", "pare", "mare", or a name). Omit it to tick everyone listed (the student and every linked parent); the preview shows who is ticked.

Without confirm=True it returns a PREVIEW (student, participants, title, text) and saves nothing. Call again with confirm=True only after the teacher approves. After saving it re-reads the new conversation and checks title, message (accents included) and participants. alu_id comes from get_roster of the tutor's class.

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": {
      "alu_id": "<alu_id>",
      "title": "<title>",
      "text": "<text>"
    },
    "name": "add_tutor_conversation"
  }
}

Input Schema

Name	Required	Description	Default
`text`	Yes
`title`	Yes
`alu_id`	Yes
`confirm`	No
`participants`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 7, 2026

TDQS

A4.9/5.0

Behavior5/5

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

With no annotations supplied, the description carries the full burden and does so thoroughly: it discloses that the notification box is never ticked (nobody is emailed), that Markdown is converted to plain text with specific preservation/removal rules, that an unconfirmed call saves nothing, and that it re-reads the record afterwards to verify title, accents and participants. These are exactly the side effects and safety facts an agent needs before a 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.

Conciseness4/5

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

The core action and its scope are front-loaded, then each parameter gets its own short block, which makes the text easy to scan. It is on the long side and repeats the preview concept twice ('The preview shows...' / 'the preview shows who is ticked'), but nearly every sentence carries operational information.

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 five-parameter write tool with an output schema, this covers everything an agent needs: authorization, ID provenance, dry-run semantics, text transformation rules, participant defaulting, and post-save verification. Return values need not be explained since an output schema exists, and the preview contents are still summarized.

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 description coverage is 0%, so the description must compensate, and it does for nearly every parameter: text (Markdown handling and conversion), participants (matched against names or roles, omitted means everyone linked is ticked), confirm (preview vs. save gate), and alu_id (source tool). Only 'title' is left implicit, which is a minor gap against otherwise strong coverage.

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?

The description opens with a specific verb and resource ('Record ONE tutor conversation (an interview summary) in a student's file') and even gives the exact navigation path ('Comunicació > Converses del tutor > Nova'). The 'ONE' emphasis and the 'interview summary' gloss distinguish it clearly from siblings like add_observation or get_session_notes.

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?

It states the authorization constraint ('Only the student's tutor can do this'), the prerequisite for alu_id ('comes from get_roster of the tutor's class'), and an explicit gating workflow: preview first, then 'Call again with confirm=True only after the teacher approves.' When-to-use and when-not-to-proceed are both spelled out.

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