Skip to main content
Glama
Sign In

Outil.io

by io.outil
OverviewDiscussionsAdmin

Upload asset

upload_asset

Importer un fichier (image/PDF/MP4/audio) depuis base64, 5 Mo maximum. Le fichier devient disponible dans la bibliothèque. Aucune amélioration par défaut. enhance:true uniquement si l’utilisateur demande explicitement une correction (luminosité, contraste, netteté légère). enhance_image permet de le faire plus tard. url pointe vers la version retenue ; asset.imageEnhancement contient original/improved et les corrections. L’original reste intact. get_image_versions compare, select_image_version choisit le défaut.

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": {
      "filename": "<filename>",
      "mime": "<mime>",
      "base64": "<base64>"
    },
    "name": "upload_asset"
  }
}

Input Schema

NameRequiredDescriptionDefault
mimeYes
base64Yes
enhanceNoDésactivé par défaut ; true uniquement sur demande explicite de l’utilisateur.
filenameYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior3/5

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

Annotations already say it is a non-destructive write (readOnlyHint=false, destructiveHint=false), and the description usefully adds that the file lands in the library, the original stays intact, and url points to the retained version. It even sketches the return object (asset.imageEnhancement with original/improved), which is strong given there is no output schema. However, it omits practical behaviors such as what happens with a duplicate filename, whether upload is idempotent, and whether any processing latency applies.

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?

Dense but orderly: purpose, limit, default behavior, opt-in condition, then return shape, then sibling routing. Every sentence carries information, though the closing sibling reference to get_image_versions/select_image_version is only loosely tied to this call and could be tightened.

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

Completeness5/5

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

With no output schema, the description still explains what comes back (url, asset.imageEnhancement contents) and that the original is preserved, and it covers the default, the size cap, and the follow-up tools. For a four-parameter upload tool this is enough for an agent to call it correctly.

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 description coverage is only 25%, so the description carries real weight: it clarifies that the 5 MB limit is on the file (the schema's maxLength is the larger base64 payload), and it repeats and sharpens the meaning of enhance beyond the schema's own note. It still says nothing about filename constraints (pattern, 191-char cap) or mime choices beyond naming broad format families.

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 states a specific verb and resource ('Importer un fichier') plus accepted formats (image/PDF/MP4/audio) and the source format (base64), so the agent can differentiate it from siblings like import_image_url or enhance_image. Scope and the 5 MB cap are front-loaded.

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 explicitly states the default behavior ('Aucune amélioration par défaut') and the exact condition for opting in ('enhance:true uniquement si l'utilisateur demande explicitement une correction'). It also names the alternatives and when to use them: enhance_image for later, get_image_versions to compare, select_image_version to set the default.

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

All Outil.io toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources