agent-intern

Overview Schema Source Related Servers Discussions Admin

Continue Antigravity conversation

antigravity_continue

Resume the exact Antigravity conversation recorded for a workspace, so follow-up prompts continue the same thread even if other sessions were used elsewhere.

Instructions

Continue the Antigravity conversation rooted at this workspace.

Resumes the exact conversation id recorded for workspace (via agy's --conversation flag), not agy's global "most recent", so it stays correct even if agy was used elsewhere in between. On agy 1.1.8+ that id is the one agy itself reported for this bridge's last run in the workspace, so a follow-up resumes THIS thread even if you have since started a separate conversation in the same folder from Antigravity's own interface.

Input Schema

Name	Required	Description
`plan`	No	If 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.
`model`	No	Optional model slug for this turn (agy's --model), e.g. "claude-sonnet-5-5-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).
`watch`	No	If true, open a live "watch" view in your browser that streams agy's steps as it works (same return value, best-effort). Default false.
`prompt`	Yes	Follow-up message.
`schema`	No	Optional 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_s`	No	Max seconds to wait for agy to complete. Default 180.
`workspace`	No	Working directory used by the prior conversation. Defaults to cwd.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.33.0Oct 21, 2026

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)."

Changed2 schema fields changedv0.28.0Aug 26, 2026

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+."
+}

Changed1 schema field changedv0.21.4Jul 24, 2026

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)."

Changed1 schema field changedv0.15.4Jul 8, 2026

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)."
+}

First observedv0.11.0Jun 18, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true, and idempotentHint=false, so the safety profile is covered. The description adds real context beyond that: it pins the resume target to the recorded conversation id for the workspace rather than agy's global 'most recent', and explains the agy 1.1.8+ recording behavior. It still omits what the tool does to the workspace (file edits/commands), but the targeting guarantee is genuinely informative.

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?

Three sentences, front-loaded with the core statement of what gets resumed, followed by the correctness rationale. Slightly dense with version-specific detail, but each sentence carries information relevant to calling it correctly.

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?

Output schema exists, so return values need no explanation, and the parameter schema is fully documented. The description covers the conversation-resumption behavior adequately; the main residual gap is any statement of side effects (file edits/command execution) or explicit contrast with antigravity_ask.

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 all 7 parameters thoroughly (plan, model, watch, schema, timeout_s, workspace). The description body adds no parameter detail of its own, 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?

States a specific verb ('Continue') plus resource ('the Antigravity conversation rooted at this workspace') and explains the resumption mechanism via agy's --conversation flag. An agent can distinguish it from its obvious sibling antigravity_ask, though the description never names that sibling 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?

Usage is implied rather than stated: the description makes clear you call this to follow up on an existing thread, but it gives no explicit when-to-use/when-not rules and never routes to antigravity_ask for starting a new conversation. Adequate but leaves the sibling decision to inference.

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