搜索文件

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

Annotations already declare idempotentHint=true, destructiveHint=false, openWorldHint=true, so the safety profile is largely covered; the description usefully adds that traversal is recursive and that symlinks are neither entered nor returned, a real behavioral constraint not in the annotations. However, it does not address the notable readOnlyHint=false for what reads as a pure query, nor limits, ordering, or permission requirements on large trees.

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?

A single front-loaded sentence with zero filler; the recursive-scope constraint comes before the symlink caveat. It is efficient, though arguably too terse for a three-parameter search tool, which is why it falls short of a 5.

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?

An output schema exists, so return-value explanation is unnecessary, and all three parameters are documented. Still missing is what an agent needs for correct invocation on large trees: result limits, ordering, whether path may point at a file, and how the symlink exclusion interacts with matching within a symlinked directory.

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 coverage is 100% (path, server, pattern all documented, including that pattern is non-empty and cannot contain path separators). The description's mention of 'filename wildcard' merely restates the pattern parameter and adds no syntax examples, glob dialect, or recursion-depth semantics beyond the schema.

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 gives a specific verb (递归搜索, recursively search), resource (文件, files under a virtual remote directory), and matching rule (按文件名通配符, by filename wildcard). It clearly separates itself from a plain listing, but it never names siblings such as list_dir or get_file_info, so an agent must infer the boundary.

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?

It states the matching mechanism and a symlink exclusion, but gives no guidance on when to prefer this over list_dir, get_file_info, or read_text_preview, and no prerequisites or exclusion conditions. The agent is left to infer usage entirely.

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