Skip to main content
Glama

Resume an Antigravity conversation

agy_resume

Continue a previous conversation by ID to send follow-up prompts, using either an ID from the ask tools or an agy conversation UUID from history.

Instructions

Continue a previous conversation by id. Accepts either a conversation id returned by agy_ask/agy_ask_new or an agy conversation UUID (as shown in agy_conversations / agy's history).

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": {
      "conversation_id": "<conversation_id>",
      "question": "<question>"
    },
    "name": "agy_resume"
  }
}

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 follow-up prompt.
workspaceNoDirectory for the agent to work in (default: AGY_WORKSPACE or the server cwd).
conversation_idYesConversation id (ours) or agy conversation UUID (from disk).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.6/5.0
Behavior4/5

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

With no annotations, the description carries the disclosure burden and does useful work: it discloses that the id may be either an internal id from agy_ask/agy_ask_new or a raw agy UUID from disk, which is exactly the kind of dual-identifier nuance an agent would otherwise get wrong. It omits mutation/queueing behavior and what happens on a stale id, so it is not exhaustive.

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?

Two tight sentences with the core action front-loaded and the identifier-format caveat immediately after. No filler, though the parenthetical reference list is slightly dense.

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?

For a 7-parameter continuation tool with no annotations and no output schema, the description covers the hardest parameter but says nothing about what a resumed turn returns (transcript delta? full history? agent output?) or how continuation interacts with mode/effort. Adequate but leaves real gaps.

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 schema already documents all seven parameters including mode, model, effort and timeout defaults. The description adds real value only for conversation_id (the dual identifier formats); everything else rests on the schema, so 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?

The description states a specific verb and resource: continue a previous conversation by id, accepting either an internal id or an agy UUID. It distinguishes itself from agy_ask/agy_ask_new implicitly by being the continuation path, though it doesn't explicitly say 'use agy_ask_new to start a fresh conversation.'

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 'Continue a previous conversation' and by naming the id sources, but there is no explicit when-to-use versus agy_ask (single-shot) or agy_ask_new (new conversation), and no stated exclusions or error conditions for an invalid or expired id.

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