Skip to main content
Glama
Sign In
@runapi.ai/gemini-omni-mcp

@runapi.ai/gemini-omni-mcp

by runapi-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

get_task

Fetch the current status and latest result payload of a gemini-omni task using its task ID, so you can poll asynchronous text-to-video jobs and retrieve outputs when ready.

Instructions

Fetch the current status and latest result payload for a gemini-omni task.

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": {
      "task_id": "<task_id>"
    },
    "name": "get_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionNoAsynchronous endpoint the task was created on. Defaults to the line's only asynchronous endpoint.
task_idYesTask id returned when the task was created.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.3.1
    • removedInput schema / additionalProperties
      Removed value: -false
  2. Changed3 schema fields changedv0.2.0
    • changedInput schema / properties / action / description
      Previous value: -"Endpoint the task was created on."New value: +"Asynchronous endpoint the task was created on. Defaults to the line's only asynchronous endpoint."
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "create_audio",
-  "create_character",
-  "text_to_video"
-]New value: +[
+  "text_to_video"
+]
    • changedInput schema / required
      Previous value: -[
-  "task_id",
-  "action"
-]New value: +[
+  "task_id"
+]
  3. First observedv0.1.0

TDQS

B3.3/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full behavioral burden, yet it only gestures at behavior via 'latest result payload' — it does not say the payload may be absent while pending, whether the call is side-effect free, or what happens on an invalid/expired task_id. For a polling tool with zero annotation coverage this is thin.

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?

One front-loaded sentence with no filler; the resource and returned data are stated immediately.

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?

With no output schema and no annotations, the description should describe the return shape, but it only summarizes it as 'status and latest result payload' without enumerating possible status values or how the payload varies by task state. Adequate for identifying the tool, incomplete for invoking and interpreting it confidently.

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?

Schema description coverage is 100% and both parameters (task_id, action) are documented, including the enum and the default for action, so the description adds no parameter meaning beyond the schema. Baseline 3 applies.

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?

Names a specific verb (fetch) and resource (current status and latest result payload for a gemini-omni task), which clearly distinguishes it from the creation-oriented siblings like text_to_video and create_character. It stops short of explicitly naming which sibling produces the task_id it consumes.

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?

The words 'current status and latest result' imply a polling workflow after an async task is created, but the description never states that this should be called after text_to_video, nor does it say anything about polling frequency or when to stop. Usage is inferred, not stated.

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