Skip to main content
Glama

delegate

Destructive

Send multi-file coding work to Antigravity's agy over ACP with auto-approved permissions; resume sessions by ID to answer clarifying questions and collect changed files.

Instructions

Delegate a coding task to Antigravity's agy over ACP. Never shell out to agy — use this tool only. Auto-approves every permission the agent requests, in any mode and anywhere on disk. Clarifying questions arrive as prose in result — resume with resumeSessionId to answer. Leave model and effort unset unless the user explicitly asks. See the delegate skill.

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": {
      "spec": "<spec>",
      "workspace": "<workspace>"
    },
    "name": "delegate"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoagent implements; plan writes a plan, returned as plan; ask answers. plan and ask are instructions to the agent, not limits.agent
specYesTask brief: goal, scope, fixed decisions quoted exactly, acceptance criteria. Sent as written. Point at files to read rather than pasting code, or attach them with contextFiles.
modelNoagy base model id, no level suffix: gemini-4-neon, gemini-3.8-flash. Omitted, agy's default runs and effectiveModel names it. doctor deep:true lists every id.
effortNoagy thinking level for the selected model (low, medium, high, xhigh). Levels differ per model; invalid values fail before the prompt and name the accepted set. Pass only when the user asks for agy effort — the host's own reasoning setting is unrelated.
workspaceYesThe agent's working directory, not a limit. Smallest directory holding the task's files; with no such directory the project root is the floor. Must already exist; never create one for the call.
contextFilesNoPaths to attach instead of pasting contents into spec. Text becomes references the agent may open; images (png/jpg/gif/webp, <5MB) are sent inline. Relative paths resolve against workspace but are not limited to it. Skips are reported in protocolWarnings, never fatal.
resumeSessionIdNoContinue an existing agy session.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.2/5.0
Behavior3/5

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

The description adds the critical behavioral fact that every permission request is auto-approved in any mode and anywhere on disk, which goes beyond the destructiveHint/openWorldHint annotations and matches them. It also discloses that clarifying questions come back as prose in the result. It does not say what else the result contains or how the session id is surfaced, so it stops short of a full behavioral picture.

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?

Six short sentences, each doing distinct work — the hard prohibition and the auto-approval warning are front-loaded. No filler or repeated schema text.

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?

For a seven-parameter, non-idempotent, open-world delegation tool with no output schema, the definition covers the risky parts: permission auto-approval, the resume loop, and default model/effort behavior. It leaves the return shape underspecified beyond clarifying questions arriving as prose, and points to an external delegate skill the agent may not have.

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 coverage is 100%, so the baseline is 3 and the schema already carries per-parameter meaning. The description adds real guidance about when to set model/effort (only on explicit user request) and how resumeSessionId is used, but nothing about spec, workspace, or contextFiles beyond what the schema states.

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?

Names a specific verb and resource ('Delegate a coding task to Antigravity's agy over ACP') and immediately separates itself from the primary alternative by forbidding shelling out to agy. An agent knows exactly what this tool is for without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit routing rules: never shell out to agy, use this tool only; leave model and effort unset unless the user asks; resume with resumeSessionId to answer clarifying questions that come back as prose. Both the when and the when-not are 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