find_duplicates

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

With no annotations provided, the description carries the full transparency burden. It discloses that the operation runs asynchronously, compares metadata or hashes content, and that sha256 is slow but accurate. This goes beyond the schema and exposes important runtime behavior.

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?

The description is compact and front-loaded with purpose, then method details, then async lifecycle behavior. Every sentence carries useful information with no filler.

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 an asynchronous tool with no annotations and no output schema, the description covers what the tool does, how to choose detection parameters, and how to stop it. It does not mention how to retrieve detection results afterward, but that is a follow-up concern rather than a blocker to correct invocation.

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 already strong. The description adds meaningful semantics for detection_method and hash_amount, explaining the tradeoffs and effect on file reads. threshold and count are not expanded, but the schema already documents them adequately.

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 opens with a specific verb and resource: 'Start Tdarr's duplicate detection', and identifies the exact API endpoint. It also differentiates itself from stop_find_duplicates by positioning itself as the asynchronous start operation.

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 explains when to choose 'metadata' vs 'sha256' and how hash_amount behaves with sha256. The async behavior is stated along with the explicit stop action, giving an agent clear operational guidance, though it does not enumerate exclusions or alternative scanning tools.

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