Skip to main content
Glama
Sign In
viraldar

viraldar

by ThomasRayvol
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Aperçu d'un carrousel

carrousel_apercu
Read-only

Generates a single contact sheet of all carousel slides, highlighting TikTok UI zones in red and text safe areas in green so you can verify no text overlaps the red zones.

Instructions

Planche contact : toutes les diapositives d'un carrousel rendu, réduites, en une image (renvoyée ici et gardée dans apercu.jpg). Les zones couvertes par l'interface TikTok sont surlignées en rouge, le cadre vert est la zone du texte (zones_sures, par défaut oui) : aucun texte ne doit tomber dans le rouge. Le cas (zone) est celui du carrousel rendu, sinon la description. Donner nom (un carrousel rendu par carrousel_rendre) ou chemins (des images quelconques, de toute taille : une image tirée d'une vidéo par montage_couverture s'y vérifie de la même façon).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "carrousel_apercu"
  }
}

Input Schema

NameRequiredDescriptionDefault
nomNo
zoneNoZone sûre : description, sans_description, pub (défaut « description » ; détail dans carrousel_modeles ou montage_infos).
cheminsNo
zones_suresNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

Beyond readOnlyHint=true, it discloses the output artifact (image returned and written to apercu.jpg), explains the red overlay for TikTok UI zones and the green frame for the text safe zone, and states the default zones_sures=yes. The disk write to apercu.jpg is disclosed but not framed relative to the read-only hint, and no size limits or failure behavior are mentioned.

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?

A single dense paragraph, front-loaded with what the image is before moving to the red/green conventions and then parameter routing. Nearly every clause carries information, though the parenthetical asides make it denser than ideal for scanning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With four optional parameters, no output schema and low schema coverage, the definition covers parameter meaning and visual conventions well, but leaves gaps: the 35-image cap on `chemins`, what happens when neither `nom` nor `chemins` is given, and the exact file location context of apercu.jpg.

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

Parameters4/5

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

Schema coverage is only 25% (just `zone`), so the description carries real weight: it explains `nom` (a carousel rendered by carrousel_rendre), `chemins` (arbitrary images of any size), `zones_sures` (green frame, on by default) and clarifies that `zone` follows the rendered carousel unless a description is given, deferring detail to carrousel_modeles/montage_infos. The maxItems=35 cap on `chemins` is not mentioned.

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?

The description states concretely what is produced: a contact sheet ('planche contact') reducing all slides of a rendered carousel into one image, returned and saved as apercu.jpg. It distinguishes this from the producer tool (carrousel_rendre) and from montage_couverture imagery, though it expresses the action as a noun phrase rather than an explicit verb.

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 routes the caller clearly: supply `nom` for a carousel produced by carrousel_rendre, or `chemins` for arbitrary images (including a frame extracted by montage_couverture, explicitly noted as checkable the same way). The purpose of the check (no text may fall in the red UI zone) is stated, but there is no explicit statement of when not to use it or of mutual exclusivity between `nom` and `chemins`.

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

Deploy Server

Other Tools