Frenchie

Generate Image

generate_image

Generate a single image from a text prompt through Frenchie. Required: prompt. Optional: style (free-text style direction), size, quality, format, background. stdio mode auto-saves the image to .frenchie//generated.; HTTP mode returns a presigned imageUrl that the agent should download for the user.

Input Schema

TableJSON Schema

Name	Required	Description
`size`	No	Optional output size. Defaults to automatic selection.
`style`	No	Optional style direction (e.g. 'flat vector, neon palette'). Merged into the generation prompt by Frenchie.
`format`	No	Optional output format. Defaults to png.
`prompt`	Yes	Required. Plain-language description of the image to generate (e.g. 'poster of a ramen shop at night').
`api_key`	No	Optional Frenchie API key (fr_...). Falls back to the FRENCHIE_API_KEY env var when omitted.
`quality`	No	Optional output quality.
`background`	No	Optional background. transparent is rejected when format is jpeg.
`output_dir`	No	Stdio mode only: absolute directory under which .frenchie/<slug>/generated.<ext> is saved. Defaults to the MCP server's process cwd. Recommended: pass your workspace root so the image lands next to your work instead of $HOME.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`jobId`	No
`result`	No
`status`	Yes
`creditsUsed`	No
`resultExpiresAt`	No
`estimatedCompletion`	No

TDQS

A4.7/5.0

Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false), the description discloses critical behavioral details: stdio mode saves to .frenchie/<slug>/generated.<ext>, HTTP mode returns a presigned imageUrl the agent must download, and transparent background is rejected with jpeg. This gives the agent actionable expectations for both invocation modes.

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

Conciseness5/5

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

Three sentences with zero waste: the first states the core action, the second lists required/optional parameters, and the third explains mode-specific behaviors. Information is front-loaded and logically ordered.

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?

Given the presence of a complete output schema, the description doesn't need to explain return values. It covers the essential mode difference, parameter usage, and a key constraint (jpeg/transparent conflict). The tool is fully contextualized within its sibling set.

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 100%, so the baseline is 3. The description adds extra value by summarizing the key parameters and explaining nuances not obvious from the schema: 'style' is merged into the prompt, 'output_dir' is only for stdio mode with a recommendation to use workspace root, and background/format constraints. This elevates it above baseline.

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 opens with a specific verb+resource: 'Generate a single image from a text prompt through Frenchie.' This clearly distinguishes it from sibling tools (e.g., ocr_to_markdown, upload_file) and states the core functionality unambiguously.

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?

The description clearly explains the two operational modes (stdio auto-save vs. HTTP presigned URL) and which parameters are required vs. optional. It doesn't explicitly name alternatives, but the sibling list makes it evident this is the only image-generation tool, so the usage context is clear without redundant exclusions.

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

All Frenchie tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose: extracting structured documents, OCR, transcription, image generation, file upload, result file download, and job status retrieval. The descriptions provide clear boundaries, so an agent can easily select the right tool.

Naming Consistency5/5

Tool names follow a consistent snake_case pattern with verb-first names (e.g., extract_to_markdown, generate_image, upload_file). Conversion tools share the _to_markdown suffix, while utility tools use verb_noun, creating a predictable and readable convention.

Tool Count5/5

Seven tools is well-scoped for a file conversion and image generation server. Each tool addresses a distinct need without redundancy or bloat, making the set feel complete yet focused.

Completeness4/5

The tool surface covers the main workflows: converting documents, images, audio/video to Markdown, generating images, and handling file uploads and downloads. A minor gap is that get_job_result only fetches the latest job, lacking support for retrieving specific job results by ID, which could hinder multi-job workflows.

Generate Image

Input Schema

Output Schema

TDQS

Glama MCP Gateway

TDQS

Resources