find_duplicates

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

With no annotations, the description carries the full burden, and it does disclose two real traits: matching is byte-exact (not similarity-based) and results are ordered by wasted space, largest first. It does not say whether the scan hits the index or the filesystem, whether it is expensive on large libraries, or whether it is purely read-only.

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 clause, front-loaded with the defining criterion and ending on the sort order; nothing is padding. It is slightly too terse to stand alone given the undocumented parameters.

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 shape need not be described, and the operation is conceptually simple. But with no annotations and zero parameter documentation, the description leaves the two knobs and the cost/scope behavior unexplained, which is more than a minimal gap for a scan-heavy tool.

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 0%, and the description never mentions 'limit' or 'folder'. Neither default (20, empty string) nor the meaning of an empty folder value is explained anywhere, so the agent must guess whether folder scopes the scan or merely filters results.

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 names the exact resource and matching criterion: groups of byte-identical documents, including matches across indexed folders. That is specific enough to separate it from find_files and search_files, which locate files rather than compare them. It is a noun phrase without an explicit verb, but the operation (group duplicates) is unambiguous.

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 never states when to use this instead of find_files or search_files, nor any prerequisite such as the index needing to be built or refreshed. 'Also across indexed folders' hints at scanning scope but is not usage guidance. The reader must infer the dedupe/cleanup scenario on their own.

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