dispatch_gemini_agent

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

With no annotations, the description carries the full burden, and it does disclose the single most important trait: this is asynchronous and returns a job_id immediately. It says nothing about failure modes (do errors surface at dispatch or later via check_agent_job), concurrency/rate limits, or the dependence on an active Antigravity IDE session.

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?

Two sentences, front-loaded with the action and finished with the async guarantee. Nothing is redundant and nothing needs to be skimmed past.

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 dispatch tool with no output schema, the description is adequate but thin: it establishes that a job_id comes back, yet does not say what else the response holds or that results must be retrieved later via check_agent_job. The rich input schema covers the request side, so the remaining gap is on the response/lifecycle side.

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 description coverage is 100%, so the baseline is 3; the schema already documents task, model (with the list_available_models routing hint), context_files, workspace_path and system_instruction in detail. The description adds no parameter-level meaning beyond what the schema provides.

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?

States a specific verb and resource: dispatch a coding/analysis/research task to a background subagent, plus the async outcome (returns job_id). It is clearly distinguishable from check_agent_job, list_active_jobs and cancel_agent_job in practice, but it never names those siblings to make the distinction explicit.

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 task classes it accepts (coding, analysis, research) plus the 'returns immediately so the orchestrator is never blocked' note give clear context for when to reach for it over a blocking call. There are no exclusions, however: nothing says what it should not be used for, and the follow-up path (poll with check_agent_job) is left implicit.

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