find_duplicatesFinds duplicate files in a directory by size grouping and SHA-256 confirmation, returning duplicate groups and reclaimable space without deleting anything.
找出目录里的重复文件：先按文件大小分组，只对同尺寸的候选算 sha256 确认，返回重复组、可回收空间。适合清理相册里重复保存的图片。只读，不删除。
| Name | Required | Description | Default |
|---|---|---|---|
| dir_path | Yes | 目录绝对路径 | |
| max_files | No | 最多扫描多少个文件，默认 3000 | |
| min_bytes | No | 只检查不小于该字节数的文件，默认 102400（100 KiB） |
Changes observed during successful MCP inspections.
v1.3.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full disclosure burden and does well: it explains the two-phase algorithm (size bucketing first, hashing only same-size candidates), states the return payload (duplicate groups and reclaimable space), and explicitly declares the read-only, non-deleting behavior. It omits operational concerns such as hashing cost on large directories and what happens when the scan limit truncates results.
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 short clauses, each earning its place: method first, use case second, safety guarantee last. No filler and the most decision-relevant content (what it returns, that it does not delete) is front-loaded or clearly flagged.
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?
No output schema exists, and the description compensates by naming what is returned (duplicate groups plus reclaimable space). What remains missing is the truncation behavior under max_files and the scope of what is not scanned, which matters for a tool that reports completeness of a directory sweep.
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%, so the schema already documents all three parameters with defaults, making 3 the baseline. The description adds conceptual meaning for the size-threshold and size-grouping logic but never mentions the max_files cap or its effect on result completeness, which is the one parameter semantic that would genuinely help an agent.
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 and resource (找出重复文件) plus the underlying method (size grouping then sha256 on same-size candidates), so the agent knows exactly what the tool computes. It does not name or contrast the nearest siblings (probe_dir, storage_report), so differentiation is inferred from the resource rather than stated.
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?
Offers one concrete use case (清理相册里重复保存的图片) which implies usage, but gives no when-not conditions, no prerequisites, and no pointer to alternative tools for related jobs such as directory probing or storage reporting.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.