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

With no annotations, the description carries the full burden and does meaningful work: it discloses per-request pricing (€0.002), the billing/auth mechanism (API key in Authorization: Bearer), the 30-label ceiling, and that results carry confidence plus a one-line reason. It omits failure behavior and does not clarify that text/labels are effectively required despite the schema marking everything optional/nullable.

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 with capability, then limits, then cost/auth, then parameters — a sensible priority order with no filler sentences. The telegraphic 'Parameters — text: text' fragment is a small readability cost but keeps the definition short.

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, so return values need not be explained, and the description still signals what comes back; cost and auth context are present. The main residual gap is that all three schema params are nullable with defaults and zero required entries, and the description never resolves whether text and labels must be supplied for a valid call.

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 0%, so the description must compensate, and it partially does: labels is documented as comma-separated (real added meaning over the bare string type) and multi as a boolean for allowing several labels. However, 'text: text' is tautological, and the description's boolean framing of multi conflicts with the schema's declared string type, leaving the agent to guess the actual accepted form.

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 — zero-shot classification of text into caller-supplied labels — plus the distinguishing constraints (up to 30 labels, single vs multi-label) and output shape (confidence + one-line reason). This separates it cleanly from sibling tools like entity_extract, image_moderate, or detect_lang without needing to name them.

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?

The clause 'Tickets, reviews, leads, moderation' gives concrete usage contexts, which is real guidance rather than none. It stops short of exclusions or alternatives — it never says when to prefer entity_extract/profanity_filter or when zero-shot classification is a poor fit.

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