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

The description adds information the annotations do not carry: per-call cost ($0.003 via x402 USDC or card key), that failed calls are free, and that repeats are charged. The last point meaningfully explains why idempotentHint=false. It does not cover latency or rate limiting, so it stops short of a 5.

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 the mechanism and outputs, then use cases, then cost/auth, then the safety note. Every sentence earns its place, though the billing/auth clause is dense enough to read as several facts packed into one sentence.

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 no output schema, the description takes on the job of describing returns (best label, reason, ranking) and does so. Combined with annotations covering read-only/non-destructive status and the schema covering limits, an agent has everything needed to call it correctly.

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 text and labels are already documented in the schema. The description restates the 2-20 label bound but adds no syntax or format detail beyond it; 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 technique (zero-shot classification), names the inputs (text plus 2-20 candidate labels) and the outputs (best label, short reason, ranking). An agent can distinguish this from ai_sentiment or ai_extract_json without opening the schema.

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?

Concrete use cases are listed: routing tickets, tagging content, intent detection, moderation queues. That gives clear positive guidance, but no explicit exclusion versus siblings that could overlap (e.g. ai_sentiment for polarity, ai_keywords for term extraction).

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