Skip to main content
Glama

ecrire_variable

Read-only

Prepares a PLC variable write without writing: validates whitelist, type, bounds, and limits, then returns a confirmation token for explicit user approval.

Instructions

PRÉPARE l'écriture d'une variable, sans rien écrire. Renvoie un jeton de confirmation.

    Contrôles : serveur en mode écriture, variable en liste blanche, inscriptible par l'automate,
    type et bornes respectés, variation limitée. Montre ensuite le récapitulatif à l'utilisateur
    et attends son accord explicite avant d'appeler confirmer_ecriture.
    

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": {
      "chemin": "<chemin>",
      "valeur": "<valeur>"
    },
    "name": "ecrire_variable"
  }
}

Input Schema

NameRequiredDescriptionDefault
cheminYes
valeurYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the annotations, it discloses that this is a two-phase prepare step that mutates nothing, that it returns a confirmation token, and that it runs a specific gate list (server write mode, whitelist, PLC writability, type/bounds, variation limits). The readOnlyHint=true annotation is consistent with 'sans rien écrire', and the description adds the preconditions and the human-approval requirement the annotations cannot express.

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?

Front-loaded with the key constraint ('sans rien écrire') and only two short blocks: contract then checks. Slight waste in the trailing whitespace and the stylized line break, but every sentence carries information.

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?

With an output schema present, the return token and recap need no expansion, and the workflow is fully specified end-to-end. The remaining gap is parameter-level detail, especially the path format, but the operational contract is complete for a prepare step.

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

Parameters2/5

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

Schema description coverage is 0%, so both required parameters carry no documented meaning. The mention of 'type et bornes respectés' implicitly constrains 'valeur' (it must match the variable's declared type and range), but 'chemin' — the identifier that selects the target variable — is never explained in format or scope.

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 in caps ('PRÉPARE l'écriture d'une variable') and immediately negates the obvious misreading ('sans rien écrire'), then names the return artifact (un jeton de confirmation). An agent can distinguish it from confirmer_ecriture purely from the text.

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 usage sequence explicitly: prepare, show the récapitulatif to the utilisateur, wait for explicit approval, then call confirmer_ecriture. That is both a when-to-use and a when-not-to-proceed rule naming the sibling that follows.

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