Skip to main content
Glama

Ask the Antigravity agent

agy_ask

Ask Google's Antigravity agent a question in a persistent, resumable conversation, letting it use its own tools and memory to solve coding and shell tasks.

Instructions

Ask Google's Antigravity agent a question in the current persistent conversation. The agent keeps its memory across calls; it can use its native tools (shell, files, browser, web search) and any MCP servers registered in agy. Returns the agent's final answer.

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": {
      "question": "<question>"
    },
    "name": "agy_ask"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoAgent execution mode (default: AGY_MODE).
modelNoModel id, see agy_models (default: AGY_MODEL).
effortNoReasoning effort (default: AGY_EFFORT).
timeoutNoTurn timeout in seconds (default: AGY_ASK_TIMEOUT).
questionYesThe prompt/question for the agent.
workspaceNoDirectory for the agent to work in (default: AGY_WORKSPACE or the server cwd).
conversation_idNoConversation to use (default: the current default). Pass an agy conversation UUID to resume a conversation from disk.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it discloses persistent memory across calls, that the agent can run native tools (shell, files, browser, web search) and registered MCP servers — implying real side effects — and that it returns the agent's final answer. It omits whether the call blocks, how failures or timeouts surface, and any permission/approval semantics.

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?

Three short sentences, each earning its place: what it does, how the agent behaves, and what comes back. The key scope constraint ('current persistent conversation') is front-loaded.

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 7-parameter tool with no annotations and no output schema, the description covers purpose, agent capabilities, memory persistence, and the return value. What is missing is operational detail an agent might want — blocking vs streaming, timeout/error behavior, and how side-effecting tool use is gated — but the core picture is complete enough to invoke correctly.

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 mode, model, effort, timeout, workspace, and conversation_id are already documented in the schema, and the description adds no parameter-level detail beyond the general note about persistent memory. Baseline 3 applies when the schema does the heavy lifting.

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?

The description states a specific verb and resource ('Ask Google's Antigravity agent a question') and scopes it to 'the current persistent conversation', which implicitly contrasts with the agy_ask_new sibling. It stops short of naming that alternative explicitly, so the differentiation is inferable rather than stated.

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?

Usage is implied by 'current persistent conversation' and the note that memory persists across calls, giving an agent enough to understand this is a continuation-style call. However, there is no explicit 'use this instead of X when Y' routing guidance against agy_ask_new, agy_resume, or agy_stop.

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