duplicate_finder

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

No annotations are provided, so the description carries the full burden. It does disclose the algorithm (size + MD5 comparison) and the return structure (groups of duplicates with paths and wasted space). However, it does not state that the operation is read-only/safe, mention recursion or symlink behavior beyond the max_depth default, or warn about the performance cost of hashing many files. Meaningful disclosure, but with zero annotation coverage, these gaps matter.

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 sentences with zero filler. The first sentence front-loads purpose and method; the second discloses the return format. Every clause earns its place.

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 3-param tool with full schema coverage and clear purpose, the description covers the core needs: what it does, how, and what it returns. The gaps are the missing safety declaration (read-only is implied but not stated, and there are no annotations), absence of performance/limitation warnings, and no explicit sibling differentiation. Adequate but with clear gaps relative to its complexity.

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%, so the schema fully documents dir_path, min_size, and max_depth. The description references the 'size' comparison, which loosely contextualizes min_size as a pre-hash filter, but adds little beyond what the schema already states. Baseline 3 applies when the schema 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 specific verb ('Find'), a resource ('duplicate files'), and the exact method used ('comparing size and MD5 hash'). This clearly distinguishes it from siblings like file_search (searching files) and code_counter (counting code), so an agent can tell them apart without opening schemas.

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 purpose implies the use case (identify duplicates in a directory), and the scope is directional rather than explicit. It does not name alternatives or state when not to use this tool vs file_stats or file_search, leaving the routing decision to inference.

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