Skip to main content
Glama

confirmer_ecriture

Destructive

Confirms and executes a prepared PLC write only after explicit user approval, using a single-use token to prevent unintended changes.

Instructions

ÉCRIT réellement dans l'automate une demande préparée par ecrire_variable.

    À n'appeler qu'après l'accord explicite de l'utilisateur. Le jeton est à usage unique.
    

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": {
      "jeton": "<jeton>"
    },
    "name": "confirmer_ecriture"
  }
}

Input Schema

NameRequiredDescriptionDefault
jetonYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false and destructiveHint=true, but the description adds the crucial operational facts: the write lands in the real machine, it requires explicit human approval, and the token is single-use. It still leaves out what happens after a successful write (confirmation, side effects) and whether an expired token is recoverable.

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, front-loaded with the emphatic 'ÉCRIT réellement', followed by the consent precondition and the token constraint. 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 destructive, one-parameter commit tool with annotations and an output schema, the description covers the essential agent-facing risks: real-world effect, mandatory user consent, single-use token. Only the failure/recovery path is missing, which is a minor gap given that an output schema exists.

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

Parameters3/5

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

Schema coverage is 0% and 'jeton' is undocumented in the schema, so the description must carry the load. It does explain the token's origin ('préparée par ecrire_variable') and its one-time nature, which is meaningful, but says nothing about the token's format, lifetime, or rejection behavior.

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 states a specific verb and resource — it actually writes a request into the PLC ('ÉCRIT réellement dans l'automate') — and explicitly ties that request to the sibling that prepared it ('une demande préparée par ecrire_variable'). That contrast with ecrire_variable is exactly what an agent needs to choose between the prepare and commit steps.

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

Usage Guidelines4/5

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

It gives a clear precondition and ordering: call only after explicit user consent, and only on a request prepared by ecrire_variable. It does not mention the abort path (annuler_ecriture) or what to do when the token is rejected, so the guidance is strong but not exhaustive.

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