interact_gemini_taskSend interactive instructions or human input to an active subagent session, optionally concluding the current turn gracefully.
向正在运行的长会话子代理（尤其处于 stream 模式的任务）注入交互式指令或人工输入，支持可选在完成当轮后优雅结束会话。
| Name | Required | Description | Default |
|---|---|---|---|
| input | Yes | 需要向子代理输入的指令或交互内容 | |
| job_id | Yes | 目标运行中任务的 job_id | |
| end_session | No | 是否在本次交互发送后自动关闭输入流，触发任务在当前轮次完成后收敛为 success 终态 |
Changes observed during successful MCP inspections.
v1.5.3Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the tool is not read-only and not destructive. The description adds meaningful behavioral detail beyond annotations: it injects input into a running stream and, when end_session is set, closes the input stream after the current turn to trigger a graceful success terminal state. No contradiction with 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?
A single dense sentence front-loads the core purpose and then adds the optional end-session behavior. Every phrase earns its place, with no filler or repetition of schema details.
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?
The definition covers the target state (running long-session, stream mode), the action (inject input), and the optional termination semantics. Annotations handle the safety profile and the schema covers parameters, so the main missing piece is return-value or failure behavior, which is not critical for invoking this 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 description coverage is 100%, so the schema already documents all three parameters. The description mirrors the input and end_session semantics but adds no new format, constraints, or usage details beyond what the schema provides, 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?
Description names a specific verb-resource pair: inject interactive instructions/human input into a running long-session sub-agent, with special emphasis on stream-mode tasks. It clearly conveys what the tool does, though it doesn't explicitly name a sibling to distinguish itself from, so it stops short of a 5.
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 clear context for when to use it: for running long-session sub-agents, especially those in stream mode. It does not list exclusions or mention alternatives like finish_gemini_task or cancel_gemini_task, so it lacks explicit when-not-to-use guidance, but the stated context is specific and actionable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.