Launch Gemini Agent

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

With no annotations, the description carries full burden. It discloses autonomous file editing, shell command execution, directory working, return of a conversation_id for continuation, auto_approve default, sandbox option, and timeout. It does not explicitly discuss destructive actions or permission requirements, but is largely transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single paragraph of six sentences, front-loaded with the primary action, followed by differentiation, usage context, return value, and model advice. Every sentence serves a purpose with no redundancy.

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

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

For a complex tool with 9 parameters and an output schema, the description covers the core behavior, usage context, sibling differentiation, return value, and model selection advice. It is well-rounded and provides sufficient context for an agent to select and invoke the tool correctly.

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

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

Schema coverage is 100%, so baseline is 3. The description does not add significant per-parameter meaning beyond the schema; it repeats the task parameter's instruction to be explicit and mentions model selection advice, but does not elaborate on other parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool delegates a task to an autonomous Gemini agent that can read/edit files and run shell commands for multi-step work, returning a final report. It explicitly distinguishes from `gemini_chat`, a sibling tool that returns a single text response.

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

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

The description specifies that the tool is for 'self-contained coding/research/automation tasks' and contrasts with `gemini_chat`. It advises model selection (Flash for speed, Pro for reasoning) and refers to the sibling `gemini_agent_models` for exact labels, providing clear when-to-use and alternative guidance.

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