Skip to main content
Glama

Send a direction correction (the director's core move)

agent_send

Send a director's corrective guidance as the next user turn to adjust the agent's direction, ensuring proper turn alternation and persisting the conversation before rerunning.

Instructions

★director 的核心动作:把方向纠正作为下一条 user 消息发出去并起下一轮(=harness 的 advance)。服务端会:把 worker 上一轮的【完整】最终结论作为 assistant 轮接上(上一轮空/被停则合成占位,保证 user/assistant 交替合法)→ 追加你的 guidance 作为新 user 轮 → 持久化 → 以当前模式重跑。若还有一轮在跑会拒绝(先 wait 或 stop)。guidance 写得像真人纠正:具体、有序、'只做第 1+2+3 步'、'每步先验证再下一步'、'只回报这 3 件事'、防兔子洞。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tidYes
guidanceYesdirector 亲笔写的方向纠正/纠矛盾/防绕圈(成为新的 user 轮)
maxRoundsNo
assistNo覆盖本轮模式;省略=沿用会话模式
Behavior5/5

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

The description discloses the full internal process: the server appends the worker's previous conclusion as an assistant turn, appends the guidance as a new user turn, persists, and reruns with the current mode. It also notes the rejection behavior when a round is active. This is highly transparent, especially given no annotations.

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

Conciseness4/5

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

The description is somewhat lengthy and mixed in language, but it is front-loaded with the core purpose and logically structured: purpose, behavior, usage guidance. Every sentence adds value, though some redundancy could be trimmed.

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?

Given the tool has 4 parameters, no output schema, and no annotations, the description covers behavioral details, rejection conditions, and usage tips comprehensively. Missing formal descriptions for 'tid' and 'maxRounds' are minor gaps, but the overall context is sufficient for an agent to use the tool correctly.

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

Parameters4/5

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

The description adds significant semantic value to the 'guidance' parameter with practical writing tips ('具体、有序、只做第1+2+3步' etc.), going beyond the schema description. For 'tid' and 'maxRounds', the schema provides coverage but the description lacks explicit details, though the context implies 'tid' is a thread ID.

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 the tool's purpose: '把方向纠正作为下一条 user 消息发出去并起下一轮', which translates to sending a direction correction as the next user message. It explicitly labels itself as the director's core move and distinguishes from sibling tools like agent_read or agent_stop.

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 usage context: it mentions that if a round is still running, the tool will reject and advises to 'wait or stop' first. It also gives detailed guidance on how to write the 'guidance' parameter, including concrete examples. However, it does not explicitly compare with alternatives among 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/WhiteNightShadow/frx-director-mcp'

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