Skip to main content
Glama
Sign In

KeelRouter

by com.keelrouter
OverviewDiscussionsAdmin

Start a video

generate_video

Start a video with a KeelRouter model and return task_id right away; videos take one to several minutes. Spends real USD from the account balance at the price in list_models (usually per second; check before choosing duration and resolution); failed calls are not charged. Then call get_result.

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_video"
  }
}

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

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true) by disclosing the two facts an agent most needs: real USD is charged at the rate found in list_models, and failed calls are not charged. It also sets latency expectations ('one to several minutes') and clarifies the call returns immediately rather than blocking.

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?

Front-loaded with the action and the immediate-return behavior, and every clause carries information (async timing, cost, failure billing, next step). The parenthetical pricing clause is slightly crammed but not wasteful.

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 tells the agent what comes back (task_id) and what to do next, and it covers cost, latency, and failure billing for a paid mutation tool. Nothing essential for a correct first call appears to be 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 already 75% (model, params, idempotency_key documented), so the baseline is high; the description adds cost-relevant meaning by tying duration and resolution choices to price. The prompt parameter and the idempotency-on-retry nuance are left entirely to 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?

States a specific verb and resource ('Start a video with a KeelRouter model') plus the key output ('return task_id right away'), which immediately distinguishes it from the blocking-style sibling get_result. An agent knows this is the async job-creation step, not a result fetch.

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?

Explicitly routes the agent forward ('Then call get_result') and points at list_models for pricing before choosing duration/resolution. It does not state when *not* to use it (e.g., prefer generate_image for stills), so it stops short of full alternative guidance.

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