Skip to main content
Glama
Sign In

KeelRouter

by com.keelrouter
OverviewDiscussionsAdmin

Generate an image

generate_image

Generate an image with a KeelRouter model. Spends real USD from the account balance at the price in list_models (from under $0.01 per image; higher resolutions cost more); failed calls are not charged. Waits up to 50 seconds; if not done, returns task_id for get_result. Result links are valid for a limited time.

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": {
      "model": "<model>",
      "prompt": "<prompt>"
    },
    "name": "generate_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelYesModel id from list_models.
paramsNoOther request fields for this model, as listed in list_models params (e.g. aspect_ratio, resolution, image_urls, duration).
promptYes
idempotency_keyNoReuse the same key when retrying so the task is not created or charged twice.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only declare the generic profile (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false). The description adds the economically critical facts annotations cannot express: real USD is spent at the list_models price, failures are not charged, and the call blocks up to 50 seconds before degrading to a task_id.

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?

Five compact clauses, each carrying distinct information — cost, failure billing, timeout, fallback handle, link expiry. The most decision-relevant fact (spending real money) is front-loaded in the second clause.

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 carries the return-value burden and does so: it explains the synchronous result link, its limited lifetime, and the task_id fallback for polling. Nothing an agent needs to invoke and handle this tool correctly is missing.

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 75%, so the schema already documents model, params, and idempotency_key. The description still adds meaning the schema lacks: cost scales with resolution, and params must be drawn from the model's entry in list_models rather than invented. That is useful guidance beyond field-level text.

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 and resource ("Generate an image with a KeelRouter model"), which immediately separates it from generate_video and list_models. It also names the provider model concept, so an agent knows this is the image-creation path.

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 agent to list_models for model ids and prices, and to get_result when the 50-second wait lapses. It does not explicitly state when to prefer generate_video over this tool, but the sibling name plus the image-specific wording makes the boundary clear without an explicit exclusion clause.

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

All KeelRouter 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