Skip to main content
Glama

InProcess Cockpit

Terminer une étape

terminer

Comme la fin d'un tour de l'agent du Studio : coulisse verify (types, règles, tests), migrations, données d'essai rechargées, puis une version enregistrée si tout passe. Sinon, les erreurs à corriger.

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": {
      "cockpit": "<cockpit>",
      "titre": "<titre>"
    },
    "name": "terminer"
  }
}

Input Schema

NameRequiredDescriptionDefault
titreYesCe qui a été fait, en une ligne, pour la personne (ex. « Devis et validation »)
cockpitYesIdentifiant du cockpit (mes_cockpits)

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

B3.3/5.0
Behavior4/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses substantial side effects: verification of types/rules/tests, migrations, and reloaded test data before a version is saved. It also states the failure path (errors to fix). It stops short of covering permissions or the shape of the returned errors, keeping it at a solid 4.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

Two sentences, no filler, but the lead sentence is an analogy that spends its budget on framing rather than front-loading the action. Dense qualifiers like "coulisse verify" add jargon that costs a little clarity without adding precision.

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 mutating tool with no output schema, the description covers the important ground: what executes, what persists (a version), and what happens on failure. It leaves the exact success/failure return payload underspecified, but the essential behavior an agent needs before invoking it is present.

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 100%, so both parameters (cockpit, titre) are already fully documented in the schema. The description adds no meaning about either — nothing on how the titre is used downstream or what a cockpit identifier must reference — so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description explains the pipeline that runs (verify of types/rules/tests, migrations, test-data reload, version saved on success), which implies finalizing a step, but it frames the action as an analogy ("Comme la fin d'un tour de l'agent du Studio") rather than stating plainly that it completes the step and records a version. An agent gets the gist but must infer the core action from the name and title.

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

Usage Guidelines3/5

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

Usage is implied by the opening analogy — call it when a unit of work is finished, before moving on. There is no explicit when-not guidance, no prerequisites, and no routing to sibling tools such as revenir_version or versions, so the agent has to infer the choice from context alone.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources