netintel_classify

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

With no annotations, the description carries the full burden and does disclose real behavior: zero-shot operation, the 2–20 label cardinality constraint, the underlying model, and the return shape (best-matching category with confidence and per-label scores) even though no output schema exists. It omits failure modes (what happens below 2 labels), latency/rate limits, and how behavior changes when multi_label is set.

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?

Two dense sentences with the core mechanism front-loaded and no filler. The trailing use-case list earns its place by scoping the tool rather than padding it.

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 a three-parameter tool with no annotations and no output schema, the description supplies the essentials an agent needs: what it returns, the model, and the label constraint. The one meaningful hole is multi_label semantics and the related single-vs-multi output behavior.

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 0%, so the description must compensate and it only partly does: it adds the '2–20 labels' cardinality rule that is nowhere in the schema, and 'text' is self-evident. The 'multi_label' parameter is never explained, and the phrase 'returns the best-matching category' (singular) actively muddies what multi_label=true would produce.

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 (classify text) plus the mechanism (zero-shot with 2–20 caller-supplied labels, Claude Haiku). The repeated emphasis on 'your own categories'/'your own taxonomy' functionally separates it from fixed-taxonomy siblings like netintel_sentiment, netintel_content_moderate, and netintel_event_classify.

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 cases — 'Route, tag, triage, and detect intent or topic' — which tells an agent the situations this fits. It never names an alternative tool or states when not to use it (e.g., use sentiment when labels are fixed), so it stops short of explicit routing guidance.

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