Skip to main content
Glama

gemini

Destructive

Query AI with model selection, sandbox code execution, and structured edit mode for code modifications.

Instructions

Query Gemini AI. Supports model selection, sandbox mode for safe code execution, and structured change mode for applying edits.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
yoloNoEnable YOLO mode (--yolo flag) to auto-approve ALL tool executions without confirmation prompts. REQUIRED when using Google Workspace extension (gemini-cli-extensions/workspace) to access Gmail, Google Drive, Sheets, Docs, Calendar, or Chat. Without this flag, Workspace extension tools will hang waiting for user approval. Set to true for any request involving Google Workspace data or actions.
modelNoGemini model to use. OPTIONS: 'gemini-3-pro-preview' (default, best quality), 'gemini-3-flash-preview' (faster, good for simple tasks). Use Flash for quick lookups or when Pro quota is exceeded. Omit to use default Pro model.
promptYesThe question or task for Gemini. REQUIRED. Use @ prefix to include files (e.g., '@src/app.ts explain the auth flow', '@package.json suggest improvements'). For code analysis, include relevant file paths. For general questions, just ask directly.
sandboxNoEnable sandboxed code execution (-s flag). Use when Gemini needs to run code, execute scripts, or test changes in isolation. Sandbox prevents modifications to your actual filesystem. Set to true for code execution tasks.
changeModeNoEnable structured edit mode for code modifications. Returns edits in OLD/NEW format that can be applied programmatically. Use when requesting code changes that need to be applied to files. The response will include exact line numbers and replacement blocks.
chunkIndexNoChunk number to retrieve (1-based). Use ONLY when a previous changeMode response indicated multiple chunks. Combine with chunkCacheKey from the original response to get subsequent chunks.
chunkCacheKeyNoCache key from a previous chunked response. REQUIRED when fetching subsequent chunks. Copy the cacheKey from the original changeMode response that contained "Chunk 1 of N".
Behavior4/5

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

The description discloses destructive behavior via changeMode and sandbox, and adds context about yolo mode for auto-approval. Annotations already indicate destructiveHint=true and openWorldHint=true, and the description aligns without contradiction.

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?

The description is extremely concise at three sentences, yet covers all key features. Parameter descriptions in the schema are equally efficient. No wasted words, and critical information is front-loaded.

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 tool with no output schema, the description explains return formats for changeMode and chunking. It covers main usage scenarios but could mention that general queries return text. Overall, sufficient for most use cases.

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?

With 100% schema coverage, the baseline is 3. The description adds significant value beyond schema: yolo flag prerequisites for Workspace, model selection advice, prompt @-syntax, sandbox/change mode explanations, and chunk handling. This greatly aids correct invocation.

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?

The description clearly states 'Query Gemini AI' as the primary purpose, with specific capabilities like model selection, sandbox mode, and structured change mode. This distinctly separates it from sibling tools like web-search or shell.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context on when to use sandbox mode for code execution and change mode for edits, and the yolo flag has detailed instructions for Workspace extension. However, it does not explicitly rule out usage compared to siblings.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/tuannvm/gemini-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server