Skip to main content
Glama

image_generate

For a user's image request, load the generating-images skill BEFORE calling this — it picks the right model and builds the prompt (this tool does neither, and calling it raw gives weak, inconsistent results).

Instructions

For a user's image request, load the generating-images skill BEFORE calling this — it picks the right model and builds the prompt (this tool does neither, and calling it raw gives weak, inconsistent results). Generate one or many still images from text prompts, optionally guided by reference images (a product photo, a character, a style or composition to follow). Pass requests: ONE object per image (wrap even a single image — { requests: [ { prompt } ] }). Generate a batch of DIFFERENT images in a SINGLE call by adding more request objects (up to 10), each with its own prompt/model/aspect_ratio/resolution/reference_images; a single approval covers the whole batch. Each result carries a hosted image URL plus a local file path, or a structured error with a hint. Use for graphics, mockups, product/marketing visuals, logos, concept art, or to render a product or character from a supplied reference. Images are polled for you; a heavy image (large model / 4k / big batch) that runs long returns {status:"pending", ...} (a job handle, not an error) — pass that exact handle to job_status to retrieve it, and never re-submit a pending image. Set dry_run=true to preview the exact requests without generating (no credits spent).Each entry in results is one of three things: finished media; a {status:"pending", ...} job handle to rejoin with job_status; or a failure carrying ok: false and an error. A failed entry is terminal — report its error and never poll or re-submit it. Read every entry rather than the top-level counters alone.

Input Schema

NameRequiredDescriptionDefault
dry_runNoIf true, return the requests that would be sent (keys masked), make no API call.
requestsYesOne object per image (wrap even a single image); add more objects to batch different images in one call (up to 10).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.13

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations, the description carries the full behavioral burden and does so thoroughly: it discloses polling behavior, the meaning of `{status:"pending"}` as a job handle rather than an error, terminal failures, dry-run behavior with no credits spent, batch approval semantics, and per-entry result handling. It also states that the tool itself does not pick models or build prompts, directing the agent to the skill.

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?

The most important instruction—load the skill before calling—is front-loaded. The description is long but earns most of its length given batch handling, pending jobs, failures, and dry-run semantics. It could be slightly tighter and better structured with bullets, and there is a minor typo ('spent).Each'), but it remains readable.

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 tool's complexity—batch image generation, reference images, pending jobs, and structured errors—the description covers what an agent needs. It explains the result entry shapes, how to handle pending versus failed entries, and how to preview requests with dry_run. With no output schema, this prose adequately compensates.

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 meaningful batching semantics beyond the schema: one request object per image, wrapping a single image, up to 10 different images per call with individual prompts/models/aspect ratios/resolutions/reference images, and one approval covering the batch. It also reinforces dry-run preview behavior, though some of that is already in the schema.

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: generate still images from text prompts, optionally with reference images. It explicitly distinguishes this from video generation by specifying 'still images' and names the sibling `job_status` for pending results. An agent can tell exactly what this tool does without opening the schema.

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 gives explicit before-calling instructions (`load the generating-images` skill), explains when to use batching versus a single request, and tells the agent to use `job_status` for pending results. It also warns against re-submitting pending images and against polling failed entries. These are clear when/when-not rules with named alternatives.

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