Skip to main content
Glama

Continue Antigravity conversation

antigravity_continue

Resume the exact Antigravity conversation tied to a workspace and send follow-up prompts, preserving the recorded thread instead of using the global most recent one.

Instructions

Continue the Antigravity conversation: resumes the thread rooted at this workspace, so pass the same workspace= as the ask (without it the sub-agent sees no repo). It resumes the exact conversation id the bridge recorded there, not agy's global most recent, so a conversation started elsewhere in between cannot take its place. model, plan and schema apply per turn. Autonomous agent: trusted prompts only.

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": {
      "prompt": "<prompt>"
    },
    "name": "antigravity_continue"
  }
}

Input Schema

NameRequiredDescriptionDefault
planNoIf true, run this turn in agy's PLAN mode (1.1.12+) — it investigates and writes an implementation plan instead of editing files or running commands, while reads still work. Per-invocation like `model`, so a follow-up can plan even if the original ask was unrestricted. See antigravity_ask's `plan` for what it does and does not guarantee. Default false.
modelNoOptional model slug for this turn (agy's --model), e.g. "gemini-4-argon-high". agy's model is per-invocation, not baked into the conversation, so a follow-up can run on a different model than the original ask — omit to use agy's settings.json default. Validated against `agy models`; an unknown slug is rejected (agy would silently ignore it).
watchNoIf true, open a live "watch" view in your browser that streams agy's steps as it works (same return value, best-effort). Default false.
promptYesFollow-up message.
schemaNoOptional JSON Schema for this turn — returns the validated object as JSON text instead of prose. Per-invocation like `model` and `plan`. See antigravity_ask's `schema`. Needs agy 1.1.8+.
timeout_sNoMax seconds to wait for agy to complete. Default 180.
workspaceNoWorking directory used by the prior conversation. Defaults to cwd.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.37.1
    • changedInput schema / properties / model / description
      Previous value: -"Optional model slug for this turn (agy's --model), e.g.\n   \"claude-sonnet-5-5-high\". agy's model is per-invocation, not baked into\n   the conversation, so a follow-up can run on a different model than\n   the original ask — omit to use agy's settings.json default.\n   Validated against `agy models`; an unknown slug is rejected (agy\n   would silently ignore it)."New value: +"Optional model slug for this turn (agy's --model), e.g.\n   \"gemini-4-argon-high\". agy's model is per-invocation, not baked into\n   the conversation, so a follow-up can run on a different model than\n   the original ask — omit to use agy's settings.json default.\n   Validated against `agy models`; an unknown slug is rejected (agy\n   would silently ignore it)."
  2. Changed1 schema field changedv0.33.0
    • changedInput schema / properties / model / description
      Previous value: -"Optional model slug for this turn (agy's --model), e.g.\n   \"claude-sonnet-4-6\". agy's model is per-invocation, not baked into\n   the conversation, so a follow-up can run on a different model than\n   the original ask — omit to use agy's settings.json default.\n   Validated against `agy models`; an unknown slug is rejected (agy\n   would silently ignore it)."New value: +"Optional model slug for this turn (agy's --model), e.g.\n   \"claude-sonnet-5-5-high\". agy's model is per-invocation, not baked into\n   the conversation, so a follow-up can run on a different model than\n   the original ask — omit to use agy's settings.json default.\n   Validated against `agy models`; an unknown slug is rejected (agy\n   would silently ignore it)."
  3. Changed2 schema fields changedv0.28.0
    • addedInput schema / properties / plan
      Added value: +{
      +  "default": false,
      +  "description": "If true, run this turn in agy's PLAN mode (1.1.12+) — it investigates\n  and writes an implementation plan instead of editing files or running\n  commands, while reads still work. Per-invocation like `model`, so a\n  follow-up can plan even if the original ask was unrestricted. See\n  antigravity_ask's `plan` for what it does and does not guarantee.\n  Default false.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / schema
      Added value: +{
      +  "anyOf": [
      +    {
      +      "additionalProperties": true,
      +      "type": "object"
      +    },
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Optional JSON Schema for this turn — returns the validated object as\n    JSON text instead of prose. Per-invocation like `model` and `plan`.\n    See antigravity_ask's `schema`. Needs agy 1.1.8+."
      +}
  4. Changed1 schema field changedv0.21.4
    • changedInput schema / properties / model / description
      Previous value: -"Optional model label for this turn (agy's --model). agy's model is\n   per-invocation, not baked into the conversation, so a follow-up can\n   run on a different model than the original ask — omit to use agy's\n   settings.json default. Validated against `agy models`; an unknown\n   label is rejected (agy would silently ignore it)."New value: +"Optional model slug for this turn (agy's --model), e.g.\n   \"claude-sonnet-4-6\". agy's model is per-invocation, not baked into\n   the conversation, so a follow-up can run on a different model than\n   the original ask — omit to use agy's settings.json default.\n   Validated against `agy models`; an unknown slug is rejected (agy\n   would silently ignore it)."
  5. Changed1 schema field changedv0.15.4
    • addedInput schema / properties / model
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Optional model label for this turn (agy's --model). agy's model is\n   per-invocation, not baked into the conversation, so a follow-up can\n   run on a different model than the original ask — omit to use agy's\n   settings.json default. Validated against `agy models`; an unknown\n   label is rejected (agy would silently ignore it)."
      +}
  6. First observedv0.11.0

TDQS

A4.1/5.0
Behavior3/5

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

Annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false) already declare this is a non-idempotent, open-world write path, and the description does not contradict them. It adds real value beyond them: thread resolution is by the recorded conversation id, not global recency, and the "trusted prompts only" note signals an autonomous agent with side effects. However it does not say what the agent may modify or what happens to the repo during a turn, so the disclosure is partial.

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?

Purpose is front-loaded in the first clause and the rest attaches concrete caveats rather than filler. The parentheticals ("(without it the sub-agent sees no repo)", "(1.1.12+)") make it dense but each earns its place; slightly tighter phrasing would improve scanability.

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?

With an output schema present, the description need not describe return values, and it correctly avoids that. It covers the main failure mode (wrong/missing workspace), per-turn parameter overrides, and the autonomous-agent risk. A note on what happens if no prior conversation exists at that workspace would close the remaining gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

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 each parameter, setting a baseline of 3. The description goes beyond it by imposing a cross-turn constraint on workspace (must match the prior ask or the repo is invisible), which is a semantic rule the schema does not state. Per-turn applicability of model/plan/schema is largely repeated from the schema.

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?

States a specific verb and resource ("Continue the Antigravity conversation: resumes the thread rooted at this workspace") and immediately differentiates itself from both antigravity_ask (same workspace as the ask) and from agy's global most-recent conversation. An agent can tell what this does and what it is not 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 Guidelines4/5

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

Gives a concrete usage condition: pass the same workspace as the original ask, and warns that omitting it leaves the sub-agent with no repo. It also clarifies that model/plan/schema are per-turn overrides so a follow-up can change mode. It stops short of an explicit "use antigravity_ask instead when starting a new thread" routing sentence, so a 4 rather than a 5.

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