委派任务给 Gemini 子代理

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

Beyond the annotations (readOnlyHint=false, destructiveHint=true, openWorldHint=true), the description adds the critical blocking trait '调用会等待结果' (the call waits for results), which materially affects agent timeout planning. It also discloses prompt transformation behavior — retaining the prompt, appending the absolute working directory, and enabling slash-command expansion for /teamwork-preview. These are genuine behavioral disclosures not encoded in the annotations.

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?

Three dense sentences with zero filler. Sentence one front-loads purpose and default model; sentence two covers prompt handling mechanics; sentence three delivers the most decision-relevant fact (blocking behavior) and the sibling routing. Every sentence earns its place, and the critical sync/async guidance is positioned as the concluding takeaway.

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 13-parameter, destructive, open-world tool with no output schema, the description covers the core UX (sync vs async, prompt handling) but leaves meaningful gaps: there is no description of the return value (conversation_id is only hinted at in the schema), no timeout or failure behavior, and no explicit warning about destructive potential beyond the annotations. Adequate, but incomplete for an agent that must decide execution parameters and interpret results.

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%, and the per-parameter descriptions are unusually rich: prompt already explains slash-command preservation and cwd appending with an example, permission_mode explains the auto-approve rationale, and timeout_seconds already carries Teamwork long-task guidance. The main description adds only marginal context (default model name, synchronous wait) that the schema largely implies, so the baseline 3 applies.

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 states a specific verb+resource pair — '通过 Antigravity CLI 调用 Gemini' (invoke Gemini via Antigravity CLI) — and names the default model. It differentiates from the async sibling start_gemini_task by explicitly declaring the synchronous behavior ('调用会等待结果') and routing long tasks elsewhere. The title '委派任务给 Gemini 子代理' reinforces the delegation semantics.

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 gives an explicit when-not condition with a named alternative: '预计超过数分钟的 Teamwork 任务请使用 start_gemini_task' (for Teamwork tasks expected to exceed several minutes, use start_gemini_task). This cleanly resolves the primary sync/async fork an agent faces. However, it offers no differentiation from the other lifecycle/status siblings (get_gemini_task, cancel_gemini_task, antigravity_status, open_dashboard), though those are largely self-evident from their names.

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