kb_find_duplicates

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

With no annotations, the description must carry the full behavioral load. It usefully discloses the ordering ('largest first'), the dedup hash, and that deletion is deferred to kb_trash, implying this call is non-destructive. It is silent on cost/scope of the hashing pass and on how the limit bounds the result set.

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 short sentences with zero filler: the first defines the output and ordering, the second defines the intended action. Front-loaded and easy to parse.

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 explanation is not required, and the mutation path is correctly outsourced to kb_trash. However, for a tool that hashes an entire library, the missing scope and limit semantics leave an agent guessing at the practical meaning of a call.

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?

There is one parameter (limit) with 0% schema description coverage, and the description never mentions it. The agent cannot tell whether limit caps the number of groups or the number of files, nor what units apply — the only hint is 'largest first', which addresses ordering, not the limit.

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 (list groups of files) plus the exact matching criterion (identical content via SHA-256) and the ordering (largest first). This is clearly distinguishable from siblings like kb_search or kb_list_tree, which do not do content-level dedup.

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?

Explicitly frames the follow-up workflow: keep one per group and remove the rest with kb_trash, naming the sibling that performs the destructive step. It gives clear positive guidance but no exclusions (e.g. when not to dedup, or whether this covers the whole library).

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