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

Annotations already declare readOnly, non-idempotent, open-world, non-destructive, so the bar is lower; the description goes further by disclosing cost ($0.01/call), the free tier (first 25, failed calls free), and the payment paths (x402 USDC or card key /credits). 'Each call is charged, so repeats are not free' usefully explains the non-idempotent hint. 'Reads or computes only and changes nothing' repeats readOnlyHint rather than adding, but does not contradict it.

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 core capability and input/output shape in the first sentence, with secondary use cases and billing in the second. The pricing sentence is dense but earns its place because cost drives re-call behavior; nothing is filler.

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 simple two-parameter tool with no output schema, the description covers what comes back (best label, reason, ranking), the cost model, and the side-effect profile. An agent has enough to decide whether to call it and what to expect in the response.

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 are documented there, so the schema carries the semantics. The description restates the 2-20 label constraint, but adds no syntax detail (e.g. how commas inside labels are handled) or guidance on label design beyond what the schema already says.

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?

The description states a specific operation with its input shape (text plus 2-20 candidate labels) and output shape (best label, reason, ranking), which is far more than the title restated. It is implicitly distinguishable from siblings like ai_sentiment or ai_moderation because the caller supplies arbitrary labels, though no sibling is named explicitly.

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 given: routing tickets, tagging content, intent detection, moderation queues. There is no explicit exclusion or comparison to overlapping siblings (ai_sentiment for polarity, ai_moderation for policy checks), so the agent must infer the boundary itself.

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