Skip to main content
Glama

ai_modeling_image_generate

Generate images from text prompts or reference images using your Studio account and a stable request_id; reuse returns the original job to prevent duplicate generation.

Instructions

text / reference images → generated images; defaults to GPT Image 2.5. Uses your Studio account and a stable request_id. Reuse returns the original job; changed input conflicts; outcome_unknown must never be blindly retried.

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": {
      "request_id": "<request_id>",
      "max_estimated_credits": "<max_estimated_credits>",
      "parameters": "<parameters>"
    },
    "name": "ai_modeling_image_generate"
  }
}

Input Schema

NameRequiredDescriptionDefault
parametersYes
request_idYes
max_estimated_creditsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.4

TDQS

A3.6/5.0
Behavior4/5

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

Annotations only declare that this is a non-readonly, open-world, non-destructive call. The description adds substantive behavior the annotations cannot: consumption of the user's Studio account, idempotency keyed on request_id, conflict-on-changed-input, and the explicit prohibition on blind retry after outcome_unknown. It stops short of explaining credit spend or failure modes beyond that one state.

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?

Three compact clauses, front-loaded with the input→output mapping and no filler. The telegraphic style occasionally costs readability (the arrow phrasing, bare 'changed input conflicts'), but nothing is redundant.

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?

For a generation tool with a three-field top level, a large nested parameter object, and no output schema, the description covers the identity/idempotency contract but leaves the credit-budget parameter and the reference-image/model selection surface undocumented. An agent could invoke it but would be guessing about cost control and parameter intent.

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?

With reported schema coverage of 0%, the description carries the burden, and it only partially does so: it explains request_id's identity/conflict semantics and confirms the model_version default. The required max_estimated_credits cap and the nested parameters object (references, resolution, scale, templates) get no explanation at all.

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 arrow notation 'text / reference images → generated images' states the transformation clearly, and naming the default model (GPT Image 2.5) grounds it in a concrete operation. It distinguishes the tool from neighbors like image_crop or image_process by implication of full generation, though no sibling is named explicitly.

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?

It gives real operational guidance on request_id reuse ('Reuse returns the original job; changed input conflicts') and the retry rule for outcome_unknown, which tells the agent how to behave on repeat calls. It does not say when to pick this over sibling generation/processing tools or what preconditions (auth, balance) must hold.

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