Find duplicate files

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

Annotations already declare readOnlyHint and idempotentHint, and the description adds substantial beyond that: verify writes temporary local files that are removed afterwards, it never deletes anything, results may be candidate-only, the walk is cached up to 5 minutes, and a first large-drive walk can take minutes. These are exactly the operational traits an agent needs.

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?

Four compact sentences, front-loaded with the detection rule, then verification side-effects, then reporting, then caching. Every clause carries information; nothing is restated from the schema or annotations.

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?

With no output schema and seven optional parameters, the description supplies the missing context: what is returned (groups, wastedBytes, suggested keeper), the safety guarantee against deletion, and the performance characteristics that affect how an agent should call it.

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 baseline is 3, but the description adds meaning the schema lacks: verify actually downloads and sha256s files (not just a boolean), and refresh is tied to the cached-walk behavior. It also names the reported fields (wastedBytes, suggested keeper), which maps conceptually to the output rather than parameters.

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 ('Find likely duplicates') and immediately defines the detection heuristic (same sha1, or same size+mediaType when sha1 is absent). No sibling tool overlaps this purpose, and the candidate-vs-verified distinction is clear.

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?

Explains when results are only candidates and when verify=true upgrades them to 'verified', plus the refresh/cache tradeoff, which tells an agent when to re-walk vs reuse. It stops short of explicitly comparing to a sibling or stating exclusions, but no sibling is close enough to warrant it.

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