Skip to main content
Glama

agy_delegate_research

Read-onlyIdempotent

Delegate deep read-only codebase research, cross-module architecture analysis, bug root-cause tracing, or security verification to Antigravity CLI; get cited Markdown analysis.

Instructions

Delegate deep read-only codebase research, cross-module architectural analysis, bug root-cause tracing, or security verification to Google Antigravity CLI (agy) using verified Gemini 3.8 Flash or Gemini 4 Argon models in --mode=plan. SERIALIZATION & ASYNC BUDGET: Calls are serialized (one at a time, AGY_MAX_CONCURRENCY = 1); a prompt that needs more than ~8 minutes of agent time should be split into one bounded question per call, or launched expecting to fetch the result by job_id via agy_job_result (soft handoff at 540s, hard watchdog at AGY_RUN_MAX_MS, cancellable via agy_cancel). WHEN TO USE: Complex multi-file reasoning or architectural audits across 5–30+ files after initial scouting. DO NOT USE FOR: Simple signature, import, or line-number extraction on known files (use local_file_scout instead at 0x quota) or parallel disjoint directory scans (use agy_spawn_swarm instead). RETURNS: Markdown analysis with : citations (or an async job_id handle if still running at soft budget) and telemetry footer.

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>",
      "tier": "<tier>"
    },
    "name": "agy_delegate_research"
  }
}

Input Schema

NameRequiredDescriptionDefault
cwdNoOptional working directory path (defaults to workspace root).
tierYesGemini routing tier: flash-low/flash-medium (1x triage), flash-high (2x module summary), argon-low/argon-medium (4x cross-module reasoning), argon-high (6x apex architecture/security).flash-medium
promptYesDetailed research or analysis prompt for Antigravity. Name the specific files to inspect. Keep to one bounded question (<~8 min agent time) or use agy_job_result if handed a job_id.
files_to_followNoOptional list of <file>:<line> targets (e.g. ["src/index.ts:42"]) to jump to in the Antigravity IDE HUD.
soft_timeout_msNoOptional soft budget in milliseconds before returning an async job_id handle (default 540000 = 540s, below the 600s client timeout).
html_artifact_nameNoOptional filename (e.g. "arch-overview.html") to instruct agy to write a self-contained visual HTML report.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.3.0
    • changedInput schema / properties / prompt / description
      Previous value: -"Detailed research or analysis prompt for Antigravity. Name the specific files to inspect."New value: +"Detailed research or analysis prompt for Antigravity. Name the specific files to inspect. Keep to one bounded question (<~8 min agent time) or use agy_job_result if handed a job_id."
    • addedInput schema / properties / soft_timeout_ms
      Added value: +{
      +  "description": "Optional soft budget in milliseconds before returning an async job_id handle (default 540000 = 540s, below the 600s client timeout).",
      +  "maximum": 590000,
      +  "minimum": 100,
      +  "type": "number"
      +}
  2. Changed8 schema fields changedv1.2.1
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / cwd / description
      Previous value: -"Optional working directory (defaults to workspace root)."New value: +"Optional working directory path (defaults to workspace root)."
    • changedInput schema / properties / files_to_follow / description
      Previous value: -"Optional list of file:line targets to jump to in the Antigravity IDE HUD."New value: +"Optional list of <file>:<line> targets (e.g. [\"src/index.ts:42\"]) to jump to in the Antigravity IDE HUD."
    • changedInput schema / properties / html_artifact_name / description
      Previous value: -"Optional filename (e.g. \"arch-overview.html\") to instruct agy to write a visual diagram/report into %USERPROFILE%\\.gemini\\antigravity\\html_artifacts\\."New value: +"Optional filename (e.g. \"arch-overview.html\") to instruct agy to write a self-contained visual HTML report."
    • changedInput schema / properties / prompt / description
      Previous value: -"Detailed research or analysis prompt for Antigravity."New value: +"Detailed research or analysis prompt for Antigravity. Name the specific files to inspect."
    • addedInput schema / properties / prompt / minLength
      Added value: +1
    • addedInput schema / properties / tier / default
      Added value: +"flash-medium"
    • changedInput schema / properties / tier / description
      Previous value: -"Gemini routing tier: flash-low/flash-medium (Tier 1 triage), flash-high (Tier 2 heavy summary), argon-low/argon-medium (Tier 3 deep reasoning), argon-high (Tier 4 apex architecture/security)."New value: +"Gemini routing tier: flash-low/flash-medium (1x triage), flash-high (2x module summary), argon-low/argon-medium (4x cross-module reasoning), argon-high (6x apex architecture/security)."
  3. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the readOnly/idempotent annotations by disclosing serialization (AGY_MAX_CONCURRENCY = 1), the async handoff mechanics (soft 540s, hard AGY_RUN_MAX_MS watchdog, cancellable via agy_cancel), and the return shape. These are the operational constraints that determine how an agent should size and sequence calls.

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?

Labeled sections (SERIALIZATION & ASYNC BUDGET, WHEN TO USE, DO NOT USE FOR, RETURNS) make it scannable and front-load the core action. It is dense and slightly over-packed with env-var names, but no sentence is filler.

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?

For a long-running, serialized, quota-consuming delegation tool with no output schema, the description supplies the return format, the async continuation path, the cancellation path, and the sizing constraint. An agent has everything needed to invoke and recover 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%, and the tier enum is fully documented in the schema including multipliers, so the description adds little per-parameter meaning. The prompt-sizing guidance ('one bounded question, <~8 min') duplicates the prompt param description, and soft_timeout_ms and html_artifact_name are not elaborated. Baseline 3 fits.

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 ('Delegate deep read-only codebase research... architectural analysis, bug root-cause tracing, security verification') and names the backing engine and mode ('--mode=plan'). It distinguishes itself from siblings by naming local_file_scout and agy_spawn_swarm with the conditions that favor each.

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?

Has an explicit WHEN TO USE clause ('complex multi-file reasoning across 5–30+ files after initial scouting') and a DO NOT USE FOR clause that routes to the correct alternatives, including the quota rationale ('0x quota'). The only minor gap is that agy_delegate_edit and agy_session_followup are not differentiated, but the core when/when-not guidance is complete.

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