Skip to main content
Glama

agy_session_followup

Resume an existing Antigravity conversation ID to ask follow-up questions while cached files remain in context; auto-compacts when usage exceeds 80%.

Instructions

Resume an existing Antigravity conversation ID (--conversation ) so previously loaded files remain in context cache, automatically compacting the session if context usage exceeds 80%. SERIALIZATION & ASYNC BUDGET: Calls are serialized (one at a time, AGY_MAX_CONCURRENCY = 1); keep follow-ups to one bounded question (<~8 minutes) or fetch in-flight runs by job_id via agy_job_result. WHEN TO USE: Multi-turn follow-up questions on an existing Session ID returned by a prior agy_delegate_research or agy_delegate_edit call. DO NOT USE FOR: Starting a brand-new research task without a prior session (use agy_delegate_research instead). RETURNS: Follow-up response, optional compaction notice, and updated session telemetry.

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>",
      "prompt": "<prompt>"
    },
    "name": "agy_session_followup"
  }
}

Input Schema

NameRequiredDescriptionDefault
cwdNoOptional working directory path.
modeNoExecution mode for the follow-up turn (defaults to plan).plan
tierNoOptional model tier override (defaults to the session model).
promptYesFollow-up instructions or question for the cached session.
conversation_idYesThe agy conversation_id UUID from a previous tool call telemetry footer (or "latest" to resume the most recent session).
soft_timeout_msNoOptional soft budget in milliseconds before returning an async job_id handle (default 540000 = 540s).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.3.0
    • addedInput schema / properties / soft_timeout_ms
      Added value: +{
      +  "description": "Optional soft budget in milliseconds before returning an async job_id handle (default 540000 = 540s).",
      +  "maximum": 590000,
      +  "minimum": 100,
      +  "type": "number"
      +}
  2. Changed7 schema fields changedv1.2.1
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / conversation_id / description
      Previous value: -"The agy conversation_id to resume (or \"latest\" to resume the most recent session)."New value: +"The agy conversation_id UUID from a previous tool call telemetry footer (or \"latest\" to resume the most recent session)."
    • addedInput schema / properties / conversation_id / minLength
      Added value: +1
    • changedInput schema / properties / cwd / description
      Previous value: -"Optional working directory."New value: +"Optional working directory path."
    • addedInput schema / properties / mode / default
      Added value: +"plan"
    • changedInput schema / properties / prompt / description
      Previous value: -"Follow-up instructions or question."New value: +"Follow-up instructions or question for the cached session."
    • addedInput schema / properties / prompt / minLength
      Added value: +1
  3. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only say readOnlyHint=false / idempotentHint=false; the description adds genuinely non-obvious traits: calls are serialized at AGY_MAX_CONCURRENCY=1, each turn should stay under ~8 minutes, long runs return a job_id fetchable via `agy_job_result`, and sessions auto-compact above 80% context. It also names what the call returns (response, compaction notice, telemetry).

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?

Front-loaded with the core action, then cleanly labeled blocks (SERIALIZATION & ASYNC BUDGET, WHEN TO USE, DO NOT USE FOR, RETURNS). It is dense but every sentence supplies decision-relevant information with no restatement of the name or schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, yet the description explicitly outlines the return payload (follow-up response, optional compaction notice, session telemetry), plus timing/concurrency behavior and the async escape hatch. That is everything an agent needs to call this correctly and interpret the result.

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% with enums, defaults, and a min/max range, so the schema already carries parameter meaning. The description only reinforces that conversation_id references a prior session's cached context (and hints at the `--conversation <id>` form); mode, tier, cwd, and soft_timeout_ms are left entirely to the schema. Baseline 3 applies.

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 ('Resume an existing Antigravity conversation ID') and immediately explains the payoff: previously loaded files stay in the context cache and the session auto-compacts past 80% usage. It also distinguishes itself from `agy_delegate_research` by requiring a prior session ID, so an agent can route correctly without opening schemas.

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 'WHEN TO USE' (multi-turn follow-ups on a Session ID from `agy_delegate_research` or `agy_delegate_edit`) and 'DO NOT USE FOR' (brand-new research with no prior session) with the alternative named. Nothing about tool selection is left to inference.

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