project_detect

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

With no annotations, the description carries the full burden and does well: it discloses the detection mechanism, the scope limit ('只探一层，不递归'), and what it returns conceptually (构建方式与常见坑). It does not discuss permissions or failure modes when no marker file matches, which keeps it short of a 5.

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?

Three tight clauses: what it does and how, when to run it, and its scope boundary. Front-loaded, no filler, and the non-recursion limitation is placed right where an agent would look for it.

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?

Return values need not be spelled out since an output schema exists, and the description still sketches them. Covers mechanism, ordering, and scope. The only real gap is the undocumented 'path' parameter.

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 single 'path' parameter has 0% schema description coverage and the description never mentions it — no statement that it defaults to '.', nor whether it accepts relative or absolute paths. With low coverage the description needed to compensate and does not.

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?

States a specific verb (识别/identify) and resource (工程目录归属生态) and even enumerates the exact marker files it keys on, which pins down the mechanism. This clearly distinguishes it from siblings like ecosystem_list and ecosystem_get, which enumerate ecosystems rather than detecting one from a directory.

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?

Gives an explicit triggering condition ('拿到别人的工程压缩包、或不知道从哪下手时先跑这个'), which is strong routing guidance. It stops short of naming an alternative tool or a when-not-to-use case, so it is clear context without exclusions.

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