Skip to main content
Glama

ask_gemini

Send a prompt, files, or a git diff to Gemini for a second opinion, code review, or large-file analysis; responses are read-only and logged for later recall.

Instructions

Ask Gemini (via the Antigravity CLI) a question or hand it a task, optionally with files as context. Gemini runs without tool access: it only sees the prompt and the inlined files. Good for second opinions and reading many large files at once.

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": "ask_gemini"
  }
}

Input Schema

NameRequiredDescriptionDefault
diffNoAttach a git diff: "staged" (index vs HEAD), "working" (unstaged), "HEAD" (all uncommitted changes), a ref, or a range like "main...HEAD". Counts against the size limit.
filesNoPaths relative to the project root (max 20 files, 500 KB total). Also accepts line ranges (src/a.ts:40-120), directories (src/) and globs (src/**/*.ts); globs and directories respect .gitignore. Contents are inlined into the prompt.
modelNoModel ID as listed by `agy models`; the suffix is the reasoning effort, e.g. gemini-3.8-flash-low | -medium | -high. Omit to use the configured default (.zwilling.json, else agy's). Higher effort is slower.
modelsNoCompare up to 4 models: the same prompt runs on each in parallel and the answers come back under one heading per model. Use instead of `model`, not together with it.
promptYesThe question or task for Gemini.
follow_upNoLog entry id of an earlier answer (e.g. g-20261113-a1b2c3, shown after every answer). Its question and answer are sent along as context. One level only: the earlier entry's own history is not included.
timeout_sNoTimeout for this call in seconds (default 120).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations only declare openWorldHint, so the description carries most of the burden, and it delivers the single most important behavioral fact: Gemini runs without tool access and only sees the prompt plus inlined files. That tells the agent the call cannot perform side effects and must be self-contained. It stops short of disclosing cost, latency, or that answers are logged for follow-up, which are left to the schema.

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?

Three short sentences, capability first, then the critical no-tool-access constraint, then the intended use cases. Every sentence carries information an agent needs and nothing is padded.

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?

For a 7-parameter tool with full schema coverage and no output schema, the description covers what it does, its key limitation, and its best-fit scenarios. The main unmentioned behavior is that answers are logged and can be referenced via follow_up, but the schema explains that, so the gap is minor.

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 each parameter (diff, files, model, models, prompt, follow_up, timeout_s) is already documented in detail. The description only echoes the file-context attachment at a high level and adds no format, limit, or interaction detail beyond the schema. 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 and resource ('Ask Gemini ... a question or hand it a task') and adds the scope qualifier that files may be attached as context. It does not differentiate itself from siblings such as gemini_task or gemini_review, and 'hand it a task' arguably overlaps with gemini_task, so an agent must infer the boundary from names alone.

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?

Gives affirmative use guidance ('Good for second opinions and reading many large files at once'), which implies when the tool is a fit. However, it names no alternative and gives no when-not conditions, so the choice against gemini_task/gemini_review 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.