push_screen把内容推到某个画布会话的屏上。参数：session_id 必填（来自 open_canvas 或 list_sessions）；content 必填，写成一条"助手回复"文本，可含 canvas-md（Markdown 卡片）/ canvas-html（完整 HTML 文档）/ ```canvas（JSON 块）围栏，围栏外文字显示为字幕；speak=true 朗读字幕；title 可选。会话在线立即上屏；不在线（含还没人打开过的）存为待展示，该会话或同岗位同一 hostUserId 下次打开自动补推。屏属于会话不属于人：别复用别人的 session_id；要执行有副作用的动作（出报告/跑检测）用 canvas_action。需要有效 Key，匿名不开。
| Name | Required | Description | Default |
|---|---|---|---|
| speak | No | 是否朗读围栏外文字 | |
| title | No | ||
| content | Yes | 含围栏的回复文本 | |
| session_id | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare the safety profile (readOnlyHint=false, destructiveHint=false); the description adds real behavioral detail absent from them: online sessions display immediately, offline or never-opened sessions are queued as pending and auto-pushed on the next open by that session or same-position/same-hostUserId. Auth requirements and session-vs-person ownership semantics are also disclosed.
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?
Purpose and required params are front-loaded, and every clause carries information; the trade-off is a single dense semicolon-chained block rather than clearly separated sections.
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?
No output schema exists, so the description must carry behavior, prerequisites and delivery semantics — and it does, including the offline queue and the cross-tool boundary with canvas_action. Nothing essential for a correct call is missing.
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?
With only 50% schema description coverage, the description compensates well: it names where session_id comes from (open_canvas or list_sessions) and explains content's fence syntax (canvas-md / canvas-html / canvas / subtitle text) plus the speak flag. Only 'title' is left unexplained.
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?
States a specific verb+resource (push content to a canvas session's screen) and immediately distinguishes scope from siblings by naming canvas_action for side-effecting work. An agent can tell what this tool owns without opening any schema.
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?
Explicit routing: use push_screen for display content, use canvas_action for actions with side effects (reports/checks). Also gives a prerequisite (valid Key, no anonymous use) and an ownership rule (never reuse someone else's session_id).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.