检索鸿蒙开发能力

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

No annotations are provided, so the description must disclose behavior. It mentions that the tool performs RAG-style retrieval, returns a capability card with usage teaching, and has a prerequisite (load SKILL). However, it does not explicitly state that the operation is read-only or has no side effects, though this is implied by '检索' (search). It adds moderate context beyond the name and schema.

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 compact, consisting of three sentences that respectively cover prerequisite, purpose, and usage workflow. Every sentence adds value: the SKILL requirement, the retrieval nature, and the follow-up with capability_run. No fluff or 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 description covers the prerequisite (load SKILL), the tool's purpose, when to use it, what it returns (capability card with parameters/examples/pitfalls), and the follow-up action (capability_run). Given there is no output schema, this sufficiently orients the agent. Minor gaps like explicit mention of pagination or default behavior are not critical for a simple search 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 coverage is 100%, with descriptions for all three parameters: query (natural language with examples), limit (return count), and category (with enum). The description does not add extra parameter details, but the schema already provides sufficient semantics. The baseline of 3 is appropriate when the schema fully documents parameters.

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 states it is a 'RAG 式检索精选能力注册表' (RAG-style retrieval of curated capability registry), giving a specific verb and resource. It also distinguishes itself from sibling capability_run by explicitly positioning this tool as the first step to find capabilities before executing them. It could more explicitly differentiate from docs_search or skills_find, but its focus on capabilities is clear.

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 clearly states that any HarmonyOS development task (构建、运行、日志、文档、技能…) should first use this tool, and that the returned capability card should then be executed with capability_run. It also gives the prerequisite of loading the deveco-unified-mcp SKILL. It does not explicitly mention when not to use it, but the workflow is well-defined.

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