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?
With no annotations, the description carries the full behavioral burden and does so: online sessions render immediately, offline (or never-opened) sessions are queued as pending and auto-pushed on the next open by that session or by the same-position same hostUserId. It also states the auth requirement (valid Key, anonymous not allowed) and the ownership constraint on session_id.
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?
Front-loaded with purpose, then parameters, then online/offline behavior, then warnings; essentially every sentence earns its place. It is delivered as one dense run-on paragraph rather than being broken into scannable segments, which slightly hurts readability but not content economy.
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 or annotations exist, so the description must cover everything, and it does: inputs, rendering semantics, deferred-delivery behavior, auth, and the ownership caveat. Nothing an agent needs to invoke this correctly 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?
Schema coverage is only 50% (title and session_id undocumented), and the description compensates fully: it marks session_id and content as required, names session_id's source, and explains content's fence syntax (canvas-md cards, canvas-html full documents, canvas JSON blocks, out-of-fence text as subtitles) plus speak=true reading subtitles and title being optional. This adds real meaning beyond the schema.
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 and resource: pushing content onto the screen of a canvas session, and immediately distinguishes itself from canvas_action (side-effect actions such as reports/checks). An agent can tell what this does and what it does not do without opening the 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?
Explicitly names the alternative for side-effect work (canvas_action), tells where session_id comes from (open_canvas or list_sessions), and gives a when-not rule: do not reuse someone else's session_id because screens belong to sessions, not people. Alternatives and exclusions are both present.
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.