Everything 结果计数

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

With no annotations and no output schema, the description carries the full burden, and it does disclose the single most important behavioral trait: the response is a count, not a file list. It omits secondary traits such as whether the count spans all mounted volumes, empty-result behavior, or performance on large indexes.

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?

Two short sentences, zero waste, with the differentiating behavior (count only, no file list) front-loaded ahead of the illustrative examples.

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 two-parameter query tool with full schema coverage, the description covers purpose, usage, and the return shape sufficiently. Minor gaps remain on result semantics and limits, but no critical information needed to invoke it correctly is missing.

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%, with query and folder both documented in the schema along with example syntax. The description adds no parameter-level detail, so the baseline 3 applies since the schema already does the heavy lifting.

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 precise behavior: it returns only the match count and deliberately does not transfer the file list, which cleanly separates it from everything_search. It never names a sibling, so an agent must infer the contrast from the semantics rather than explicit routing.

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?

Concrete example questions («我电脑上有多少个 PDF», «这个目录里有多少张图») make the intended usage obvious, and the count-only framing implies you should pick this over a listing search when you only need a number. It stops short of explicitly naming the alternative tool or stating when this is the wrong choice.

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