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

Goes well beyond the annotations, which only declare read-only/idempotent/no-open-world. The description adds that `verified` is always false because the UA is self-reported and no IP or reverse-DNS checks are performed, discloses the underlying parser and version (ua-parser-js 1.0.41), the curated bot-list size and snapshot date (151 bots, 2026-10-08), and the independent/non-affiliated stance. This is exactly the behavioral context annotations cannot carry.

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?

Front-loads the core action and result set in the first sentence, then layers caveats and provenance. It is dense but not padded; the corporate non-affiliation sentence and list snapshot date are borderline, yet each clause carries informational weight.

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 an output schema present the return shape need not be explained, and the description still supplies the essential caveat (verified always false) plus provenance. The one soft spot is 'same engine and limits as the UAParse JSON API,' which alludes to limits without stating them (e.g., rate limits), leaving an agent to guess at throughput constraints.

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 100% and both parameters (ua, include_raw) are fully documented in the schema, so the baseline is 3. The description adds output semantics (what the classification fields mean) rather than any additional parameter meaning, so it does not raise the score above baseline.

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?

Opens with a specific verb + resource ('Parse one User-Agent string') and enumerates exactly what it extracts (browser, engine, OS, device, CPU, bot/AI-crawler classification). There are no siblings to distinguish from, but the scope statement 'one User-Agent string' and the enumerated outputs leave no ambiguity about what the tool does.

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?

Gives clear operative context: parse the UA exactly as sent in the header, each call is one lookup, read-only with no network lookups, and the same engine/limits as the JSON API. It does not state explicit when-not-to-use conditions or name alternatives, so it falls short of a 5, but the usage envelope is clear.

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