Skip to main content
Glama

InProcess Cockpit

Regarder un écran de l'aperçu

regarder_ecran

Ouvre une page de l'aperçu en tant qu'un compte d'essai : texte visible, erreurs, capture. Peut jouer un parcours (étapes : click, fill, choose, check, uncheck, expect, expect_absent, goto).

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>"
    },
    "name": "regarder_ecran"
  }
}

Input Schema

NameRequiredDescriptionDefault
clicsNoTextes à cliquer dans l'ordre avant de lire la page
cheminNoPage de l'aperçu, ex. /devis (par défaut /)
etapesNo
captureNoJoindre une capture (par défaut oui)
cockpitYesIdentifiant du cockpit (mes_cockpits)
telephoneNoÉcran de téléphone (390 px) au lieu d'un ordinateur
en_tant_queNoEmail, nom ou rôle d'un compte d'essai

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A3.7/5.0
Behavior4/5

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

Annotations only supply readOnlyHint=false and destructiveHint=false, so the description must carry most of the behavioral burden — it does add real signal: the page is rendered under a trial account (sandbox framing), the response includes visible text, errors and a screenshot, and journey steps can be executed. It still omits whether journey actions persist or mutate trial state, and says nothing about timing, rate limits or failure modes when a step does not match.

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?

Two dense sentences, front-loaded with the core action and output before the optional journey capability. The only near-waste is re-listing the eight action names already present in the schema enum, but that aids discoverability at low cost.

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 seven parameters, one required, and no output schema, the description helpfully characterizes what comes back (visible text, errors, screenshot) and adds the journey mode. It remains silent on how the default path works, what happens on an unmatched step, or how this differs from adjacent preview/inspection tools, which keeps it shy of complete.

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 description coverage is already 86%, covering chemin, capture, cockpit, telephone and en_tant_que. The description reinforces the trial-account semantics of en_tant_que and enumerates the step actions, but the action list duplicates the schema enum rather than adding meaning, and the distinction between clics and etapes is left entirely to the schema.

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

Purpose4/5

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

States a specific verb and resource ('Ouvre une page de l'aperçu') and specifies the actor context ('en tant qu'un compte d'essai') plus the output ('texte visible, erreurs, capture'). The added capability ('Peut jouer un parcours') clarifies scope further. It does not name or contrast any sibling tool, so it falls short of a 5.

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 rather than stated: the agent can infer this is for inspecting a preview page and optionally replaying a user journey as a trial account. There is no explicit 'use this when…' or 'use X instead when…' guidance, and related siblings like version_demo or avant_publication are never referenced.

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