检索官方文档

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

With no annotations, the description carries the full transparency burden. It discloses the corpus scope and included document categories but does not describe result behavior (e.g., snippets, paths, relevance ordering) or any side effects. This is adequate but not more.

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 only three sentences: prerequisite, function, and usage context. Every sentence contributes meaningful operational guidance, and the most important prerequisite is front-loaded. No wasted words.

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?

For a search tool with no output schema, the description covers the corpus, scope, and when to use it, and points to the SKILL manual for workflow standards. It does not explicitly mention how results should be consumed (e.g., via docs_read), but the schema and SKILL reference fill most gaps.

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 input schema covers 100% of parameters with descriptions, defaults, enums, and examples. The tool description adds general purpose and use-case context but no parameter-specific meaning beyond what the schema already provides. Baseline of 3 is appropriate.

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 uses a specific verb ('全文检索') and a clearly defined resource: local 2000+万字 HarmonyOS 官方文档 across enumerated categories. It distinguishes this search tool from sibling read/browse tools by positioning it as the pre-coding lookup 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 gives explicit usage context: before writing ArkTS/ArkUI code, when unsure about an API, component, or concept. It also mandates loading the SKILL first as a prerequisite. However, it does not explicitly name sibling alternatives or state when not 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.