gemini-pro-mcp

Overview Schema Source Related Servers Discussions Admin

gemini_code

Destructive

Delegates a coding task to Gemini to read and edit files in a local project folder, then returns a summary and conversation ID for follow-up changes.

Instructions

Delegate a coding task to Gemini, which reads and EDITS files in one local folder through the Antigravity agent on the user's Google AI Pro plan (no API cost). This changes files: tell the user, and review the result afterwards, e.g. with git diff. Terminal commands run in a sandbox and only the given folder is writable.

    Good for a well-defined change: fix a bug, add tests, refactor a module.
    For read-only questions use gemini_ask; for a task on a GitHub repo that
    should end in a pull request use jules_start.

    Args:
        task: What to change and how to know it is done, e.g. "Add unit tests
            for parse_date in utils/dates.py; all tests must pass".
        folder: Absolute path of the project folder Gemini may edit.
        model: Model id from gemini_models; omit for agy's default.
        agent: Name of an Antigravity agent from gemini_agents to run the task.
        effort: Reasoning effort: "low", "medium", "high", "xhigh" or "max".
        conversation_id: Continue an earlier gemini_code or gemini_ask chat, e.g.
            to ask for fixes to the previous change.

    Returns:
        Gemini's summary of what it changed, and a conversation_id for follow-up
        requests; or an error if the folder does not exist.

Input Schema

Name	Required	Description	Default
`task`	Yes
`agent`	No
`model`	No
`effort`	No
`folder`	Yes
`conversation_id`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 7, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already flag destructive/openWorld/non-idempotent, and the description adds concrete operator guidance beyond them: tell the user before running, review with `git diff` afterwards, terminal commands are sandboxed, only the given folder is writable, no API cost, and a failure mode (error if the folder does not exist). This is unusually rich behavioral context for a mutating tool.

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?

Front-loaded with the most important fact (this changes files) followed by safety guidance, then fit, then parameters. Dense and mostly waste-free, though the Returns block partly restates what the output schema already carries.

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?

Covers the mutation risk, sandbox constraints, prerequisites for optional parameters, sibling routing, and error behavior — everything needed to call a destructive six-parameter tool correctly. An output schema exists, so the brief return summary is sufficient rather than a gap.

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

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must carry the full load and does: task is defined as change-plus-done-criteria with an example, folder as an absolute path that Gemini may edit, model and agent are tied to gemini_models/gemini_agents with omission semantics, effort enumerates its five values, and conversation_id explains continuation across both gemini_code and gemini_ask.

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 a coding task to Gemini') plus the exact scope: reads and edits files in one local folder via the Antigravity agent. It explicitly names the siblings it is not (gemini_ask for read-only, jules_start for GitHub PR tasks), so an agent can disambiguate without opening any schema.

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?

Gives positive guidance ('Good for a well-defined change: fix a bug, add tests, refactor a module') and explicit exclusions routed to named alternatives. The follow-up path via conversation_id is also framed with a concrete use case ('to ask for fixes to the previous change').

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

Deploy Server