PDS 文档检索

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

With no annotations, the description carries the full disclosure burden and delivers: it states chunks are '直接可用' (directly usable), PDF paths are returned for the host agent to Read, and the no-query fallback returns a manual list. It also reveals the cost profile ('无 embedding、零额外成本'), a useful behavioral trait absent from schema/annotations. It stops short of describing zero-result behavior or result ordering.

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?

Four dense sentences with zero filler: the action is front-loaded, the two-tier return contract follows immediately, parameter behavior is packed into the middle, and the cost note closes it. Every sentence earns its place relative to a 4-parameter tool.

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 moderate-complexity search tool with no output schema, the description competently sketches the return contract (chunk text vs PDF path) and default behaviors. The remaining gaps are minor: no explicit return structure/ranking details and no pointer to the sibling msim_doc_search for non-PDS documentation.

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 baseline is 3, but the description adds genuine meaning beyond the schema: it enumerates what chunks contain (Tcl/编译流程/扫链烧录/ILA 调试), gives the exact registry size (21+62), and clarifies that 'semantic' mode does not rely on embeddings. This meaningfully supplements the bare parameter names.

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 opens with a specific verb+resource ('检索 PDS 文档层') and explains the two-tier result structure: distilled text chunks that are directly usable versus PDF paths the host agent can Read for 21 PDS manuals + 62 IP datasheets. This scoping clearly differentiates it from sibling fpga_msim_doc_search (MSIM docs) and fpga_ip_lookup without ambiguity.

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?

Provides clear usage context: query drives keyword recall, kind restricts scope to all/chunk/manual/datasheet, and omitting query returns the manual list. However, it never names alternatives or exclusions — notably the near-twin sibling fpga_msim_doc_search — so an agent gets context but no explicit when-not-to guidance.

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