Skip to main content
Glama

副席工位直聊发送

app_boss_send

Starts an asynchronous message send from the SideDesk side pane to the active persona card, with permission controls and image attachments for direct UI interactions.

Instructions

UI 专用:用户在副席直接给当前人物卡发消息(<50ms 瞬时异步启动,支持三组权限胶囊与图片附件)。

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": {
      "sourceDir": "<sourceDir>",
      "prompt": "<prompt>"
    },
    "name": "app_boss_send"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNo
titleNo
promptYes
sandboxNo
fastModeNo
personaIdNo
sessionIdNo
sourceDirYes
attachmentsNo
permissionsNo
reasoningEffortNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.4/5.0
Behavior2/5

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

No annotations exist, so the description carries the full burden. It does add real behavioral context — sub-50ms async initiation, three permission capsules, image attachments — but says nothing about what the async start produces, failure behavior, idempotency, or whether a session/persona must already be open.

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

Conciseness3/5

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

It is a single front-loaded sentence with no filler, which is good. But the parenthetical packs three unrelated facts (latency, permissions, attachments) and reads as marketing rather than orienting information, so density comes at the cost of clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter tool with nested objects, no output schema, and no annotations, the description is far too thin. An agent cannot determine required inputs, the effect of the permissions object, or what happens after the async job starts.

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

Parameters2/5

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

Schema description coverage is 0% across 11 parameters, including nested permissions and attachments objects. The description hints at the three permission groups and image attachments, which map to a few parameters, but the required sourceDir and prompt, plus personaId, sessionId, sandbox, fastMode, model, reasoningEffort, and title, are entirely unexplained.

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

Purpose3/5

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

The description names a specific action (sending a message to the current persona card in the side desk) and marks it as UI-only, so the agent can infer the basic effect. However, it never distinguishes this from dispatch-style siblings like sidedesk_dispatch or sidedesk_open, and the jargon ('副席工位直聊') leaves the exact scope ambiguous.

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

Usage Guidelines2/5

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

The only usage signal is 'UI 专用', which restricts callers rather than explaining when to pick this tool over the dispatch/job siblings. There is no stated precondition, no exclusion, and no indication of what a caller should do instead when not driving the UI.

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