Executes only a human-approved Discord server plan from the local window within 10 minutes, backs up before changes, enforces one-time approval, and rejects plans with changed targets.
Exécuter uniquement un plan approuvé par l'humain dans la fenêtre locale, depuis moins de 10 minutes. Sauvegarde avant toute mutation. Approbation à usage unique. Refuse un plan dont les cibles ont changé.
| Name | Required | Description | Default |
|---|---|---|---|
| plan_id | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full burden, and it delivers unusually strong safety context: a pre-mutation backup, single-use approval, a 10-minute freshness window, and refusal when targets drift. It stops short of describing failure modes, atomicity, or what the caller receives on success.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four short sentences, zero waste, with the core execution constraint front-loaded ahead of the safety and refusal rules. Every sentence adds a distinct operational fact.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a mutating executor with no annotations and no output schema, the description covers preconditions, safety behavior and refusal semantics well. The main omission is the return side — with no output schema, the agent does not know what an execution result looks like.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There is one parameter (plan_id) with 0% schema description coverage, so the description must compensate. 'Un plan approuvé' implies plan_id points at an approved plan, but it never says where that identifier comes from (presumably a preparer_plan/consulter_plan result), so an agent must guess.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific verb and resource ('Exécuter ... un plan approuvé') and constrains it with 'uniquement', which distinguishes it from the plan-lifecycle siblings such as preparer_plan, consulter_plan and annuler_plan. It does not explicitly point at a sibling, but the action is unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Preconditions are explicit: the plan must already be human-approved in the local window, be under 10 minutes old, and have unchanged targets. What it does not do is name the sibling that produces the approval (ouvrir_approbation) or state which tool to call first, leaving the workflow order to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.