浏览文档目录树

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

No annotations are provided, so the description carries the full burden. It discloses an important prerequisite (loading the deveco-unified-mcp SKILL) and explains behavioral context: the tree structure, page titles, and the fact that page paths serve as document IDs for docs_read. This goes beyond basic function naming, though it omits details like output format or pagination, which are not critical for a simple browsing tool.

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?

The description is three sentences long and every sentence earns its place: the first states a prerequisite, the second defines the core function, and the third explains output usage and connection to docs_read. It is front-loaded with the most important operational requirement and contains no redundant fluff.

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?

Given the absence of an output schema, the description adequately communicates the return concept (directory tree with categories, chapters, pages, and titles) and how to use the results (path as document ID). It covers the workflow and relationships with sibling tools. Some details like depth behavior are already in the schema, so the description is complete enough for a straightforward browsing tool.

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%, with each parameter (path, depth, catalog) already having clear descriptions in the input schema. The tool's description adds no extra parameter-level meaning; it only mentions that page paths can be used as document IDs, which is output-related rather than parameter-specific. Baseline 3 is appropriate since the schema handles parameter semantics.

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 clearly states the tool's function: '浏览官方文档库目录树（分类→章节→页面，页面附标题）' (browse official documentation library directory tree: category→chapter→page, pages have titles). It uses a specific verb plus resource and identifies the hierarchical structure, distinguishing it from sibling tools like docs_search and docs_read by positioning it as the initial navigation step.

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?

The description provides explicit workflow guidance: '先目录定位再全文检索再读全文' (locate via catalog first, then full-text search, then read full text), and notes that page paths from this tool can be used directly with docs_read. It clearly indicates when this tool should be used relative to search and read tools, though it does not explicitly mention when not to use it or compare with docs_catalog.

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