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

Annotations already cover safety (readOnly, non-destructive, openWorld=false), and the description adds genuinely new context: the exact similarity metric, the returned fingerprint, the per-call batch cap, and a cost/auth model (x402 client-paid, $0.01 per success, failures free). That payment and billing behavior is exactly the kind of thing annotations don't convey.

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 tight sentences, front-loaded with purpose then mechanism, limits, and cost. No filler; every clause carries information.

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?

Cost, batch limit, algorithm, and returned SimHash are covered without an output schema needing more. The remaining gap is how duplication results are reported (pairwise matches vs groups) and how documents are passed, which an agent would still need.

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?

Zero parameters, so the baseline is 4, but the description talks about 'a batch of documents' while the schema is an empty object — leaving the agent unclear on how documents are actually supplied. That mismatch between described input and the empty schema costs a point.

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 (near-duplicate detection) and resource (batch of documents), and even names the decision mechanism (Jaccard over word-3-shingle sets) and per-document artifact (64-bit SimHash). This distinguishes it from siblings like hash or diff at a glance.

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 gives a concrete operating bound (up to 200 documents per call) and implies the batch context, but never says when to prefer it over hash or diff, nor any preconditions/exclusions. Usage is implied rather than guided.

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