能力目录 (分层)

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does so well by revealing that the tool returns cost/safety notes and that serverVersion acts as a runtime code fingerprint whose mismatch with the working tree HEAD indicates stale service requiring restart. It does not explicitly state 'read-only', but the return-oriented phrasing and the absence of mutation language make the safety profile reasonably transparent.

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 dense, front-loaded sentences with no filler. The first sentence states the primary return value and purpose; the second adds a critical ops detail about serverVersion. Every clause contributes useful information for invocation.

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?

Despite having no output schema and no annotations, the description explains the main return kinds (catalog, long-tail routing, cost/safety notes, serverVersion) and even interprets the serverVersion semantics. For a parameterless discovery tool, this is sufficient for an agent to understand what it will receive and why it matters.

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 tool takes zero parameters and the schema description coverage is 100%, so there is nothing meaningful for the description to add about parameters. According to the zero-parameter baseline, a score of 4 is appropriate because the description correctly focuses on return content rather than inventing parameter details.

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 a clear verb-resource pair: it returns a layered tool catalog (tier0 hot/tier1 common/tier2 expert) plus a server version fingerprint. It clearly differentiates itself from sibling tools by positioning itself as the discovery entry point to the complete PDS control plane, rather than a tool that performs an FPGA operation.

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 explicitly says it is '用于发现完整 PDS 控制面' (used to discover the complete control plane) and notes that long-tail capabilities are reached via fpga_cdt/fpga_exe, which gives the agent routing guidance. It does not explicitly state when not to use it, but the discovery-oriented framing is clear enough.

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