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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the safety profile is covered. The description adds genuinely external-behavioral context: the Jev primary backend with a Groq-hosted LLM fallback and a hard 'under 4.5s guaranteed' latency bound, which materially affects how an agent schedules and retries this call.

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-loaded and dense: capability, label count, output shape, and reliability all land in the first two clauses with no filler. The trailing 'Try GET /classify/sample' is a useful discovery pointer, though the dash-chained structure makes it slightly harder to scan than separate sentences.

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 and the description still names the return fields (confidence, alternate label), which is a bonus rather than a redundancy. Safety hints and latency are covered, so the only omission is failure behavior for oversized text or unavailable backends, which is minor for a two-param read-only tool.

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%, so both parameters are fully documented in the schema (text up to 4000 chars, 2-20 labels). The description restates the 2-20 label bound and adds no syntax, escaping, or label-selection guidance beyond it, so the baseline 3 applies.

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+resource ('text classification') and is unusually precise about mechanics: custom labels (2-20), confidence score, alternate label, and a latency/fallback story. However it never positions itself against obvious siblings like sentiment, intent, spam_check, or toxicity, so an agent must infer the distinction from the phrase 'your own custom labels' alone.

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 concrete use-case examples ('a support ticket, a review, or any text') which implies when the tool fits, but offers no explicit when-not and never names an alternative. For a cluster containing sentiment, intent, spam_check, and toxicity, the absence of routing guidance between fixed-label and custom-label classifiers is a real gap.

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