读取文档全文

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

No annotations are provided, so the description carries full burden. It discloses that the tool retrieves full markdown content and that SKILL loading is required, which are useful behavioral details. It doesn't address error handling or side effects, but for a read-only docs tool, this is adequate.

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 two concise sentences, front-loaded with the prerequisite and then the core purpose. Every sentence earns its place without redundancy.

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?

The tool is simple (one ID parameter). The description covers the return format (full markdown), required prerequisite (SKILL), and ID source (docs_search). It references SKILL.md for more detail. Minor gaps like error behavior don't significantly impair completeness.

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?

The schema already fully describes the single parameter with an example. The description adds crucial semantic context: the document ID must come from the documentId field of docs_search results, preventing arbitrary or guessed IDs. This goes beyond 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?

The description clearly states the action (read by document ID), the resource (HarmonyOS official documentation), and the output format (markdown). It distinguishes itself from sibling tools like docs_search (which searches) and docs_catalog/docs_tree (which browse).

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 explicitly instructs to load the deveco-unified-mcp SKILL before use and states that the document ID must come from docs_search results, effectively giving the workflow: search first, then read. This is clear guidance on prerequisites and data source, distinguishing when to use this tool.

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