Skip to main content
Glama
Sign In
dayuan-lite

dayuan-lite

by lighters
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

dayuan_read_reply

Idempotent

Answer text clarification prompts for pending read-only WeCom queries only when replies are allowed, returning status and avoiding approvals, cancellations, or replays.

Instructions

仅在 input_required 且 interaction.reply_allowed=true 时回答原只读任务的文本澄清。审批卡和未知结构返回原任务及 reply_sent=false，不发送、审批或取消。parent_request_id 为最初查询 ID，每次回复使用独立稳定 request_id；不确定结果禁止重放。

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "request_id": "<request_id>",
      "parent_request_id": "<parent_request_id>",
      "answer": "<answer>"
    },
    "name": "dayuan_read_reply"
  }
}

Input Schema

NameRequiredDescriptionDefault
answerYes
request_idYes
wait_secondsNo服务端在本次调用内按同一 request_id 轮询结果的最长秒数（0–30）；到时仍未完成则返回当前状态。
parent_request_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

Adds behavior beyond the annotations: on approval cards or unknown structures it returns the original task with reply_sent=false rather than mutating, and it forbids replay on uncertain outcomes. These are exactly the failure-mode details the openWorldHint/idempotentHint annotations cannot convey.

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

Conciseness5/5

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

Three tight sentences: gating condition first, edge-case return behavior second, identifier discipline third. No restatement of the tool name or filler.

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?

Covers the return-signal (reply_sent=false) despite no output schema, and explains the identifier contract for a mutation-flagged tool. Minor gap: the 'answer' field's content expectations for a 2000-char payload are left to inference.

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?

Schema coverage is only 25% (only wait_seconds is documented), so the description has to compensate, and it does for two of the three undocumented params: parent_request_id is defined as the original query ID and request_id as a per-reply stable unique ID with a no-replay rule. 'answer' is only implied by '文本澄清', leaving one gap.

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

Purpose4/5

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

States a specific verb ('回答/回复' the text clarification) applied to a specific resource ('原只读任务'), and pins the scope to a reply to an existing read task. It does not name read_start/read_result explicitly, but the 'only when input_required' framing makes it distinguishable from the initiating siblings.

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

Usage Guidelines5/5

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

Gives an explicit gating condition for when to call (input_required AND interaction.reply_allowed=true) and explicit exclusions for what it must not be used for (审批卡、不发送、不审批、不取消). The '不确定结果禁止重放' line tells the agent when NOT to retry.

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

Deploy Server

Other Tools