浏览、搜索或查看 Metadata 任务。传 task 返回单任务详情；传 query 搜索任务和 action；都不传则按 group 分页列出任务摘要。
| Name | Required | Description | Default |
|---|---|---|---|
| task | No | 可选任务 ID，例如 family_space.manage_room；传入后返回该任务详情和 action 摘要 | |
| group | No | 可选分组 ID，例如 family_space | |
| limit | No | 最多返回多少个任务 | |
| query | No | 可选搜索关键词，例如 room、房间、device、automation | |
| cursor | No | 分页游标；来自上一次返回的 nextCursor |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full behavioral burden. It does disclose mode-dependent behavior (single detail vs. search vs. paginated summary, and that query spans actions too), which is genuinely useful, but says nothing about read-only nature, result volume, or limits beyond what the schema already states.
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?
A single compact sentence with three clearly delimited clauses, front-loading the browse/search/view framing before the branch conditions. No filler, though the three modes run together without separators.
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?
An output schema exists, so return-value detail is not needed here, and the branching logic across the five optional parameters is fully explained. Complete enough to invoke correctly; only cross-tool routing guidance is absent.
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 description coverage is 100%, so each of the five parameters is already documented with examples in the schema. The description reinforces the mode semantics of task/query/group but adds no format, constraint, or interaction detail beyond what the schema provides.
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?
The description gives a concrete verb set (浏览/搜索/查看) bound to a specific resource (Metadata 任务) and enumerates three operating modes keyed to which parameter is supplied. It is distinguishable from list_actions and list_groups by resource, but it never names or contrasts those siblings explicitly.
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?
It gives explicit conditional guidance: pass task for a single-task detail view, pass query to search tasks and actions, pass neither to get group-paginated summaries. That covers when to use each mode well, but offers no guidance on when to prefer a different tool (e.g. list_actions or execute_task) instead.
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.