Skip to main content
Glama
Sign In
antigravity-mcp

antigravity-mcp

by zwsxzy
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

dispatch_gemini_agent

Dispatches coding, analysis, or research tasks to a background Gemini subagent and returns a job_id immediately, so orchestration continues without blocking.

Instructions

Dispatch a coding, analysis, or research task to a background Antigravity subagent. Returns immediately with a job_id so the orchestrator is never blocked.

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": "<task>"
    },
    "name": "dispatch_gemini_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskYesProject execution: GPT-reviewed independent multi-parent plan; administrative diagnostics may use ordinary task text.
modelNoWhich live model to run this job on, e.g. 'Gemini 3.8 Flash (High)'. The live catalog (versions, families, and thinking-effort tiers) changes over time and depends on the connected Antigravity IDE session — call list_available_models rather than assuming a name. Defaults to Gemini 3.8 Flash (High), loaded from persistent MCP workflow settings.
context_filesNoOptional absolute file paths to include as context for the agent.
system_instructionNoCustom system instructions for the subagent worker.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full burden and does disclose the key trait: execution is asynchronous and returns a job_id immediately. It omits other behavioral facts an agent would want, such as concurrency limits, whether failures surface only via polling, or the dependency on a live Antigravity IDE session mentioned only inside the model parameter schema.

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?

Two sentences, zero filler, with the core action first and the non-blocking guarantee second. Nothing could be removed without losing information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, and the description correctly states the return value (job_id) plus the non-blocking contract, which is the essential return information. It stops short of describing what happens on failure or what the caller should do after receiving the job_id.

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%, so the schema already documents task, model, context_files, and system_instruction in detail, including the pointer to list_available_models. The description adds no parameter-level meaning beyond what the schema provides, so the baseline of 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?

States a specific verb (dispatch) and resource (background subagent task), plus the task categories it covers (coding, analysis, research) and the immediate return of a job_id. That distinguishes it from siblings like check_agent_job or cancel_agent_job, which operate on existing jobs, 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?

Implies the use case through 'so the orchestrator is never blocked,' signalling fire-and-forget dispatch rather than synchronous work. It never states the companion flow (follow up with check_agent_job/get_agent_job_status) or when a caller should not use it, so the guidance is inferred rather than 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