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

With no annotations, the description carries the behavioral burden and does disclose two costly-to-discover facts: the 0.002 USDC per-call price and the x402 payment protocol, plus the hard 50-text batch cap. It does not say what happens beyond 50 texts (error vs. truncation) or whether billing is per call or per text, which leaves a real gap.

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 sentences, no filler: output shape and limits first, then price and payment protocol. Every clause carries information an agent needs before calling.

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?

Dimension, batch limit, cost, payment mechanics and use cases are all covered without an output schema, so an agent can call it correctly. Missing only edge behavior (over-limit handling, per-text vs. per-call billing) for a paid 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 already documented, including the array form of 'text' and the full 402 payment retry flow. The description adds only the 50-item ceiling, which the schema leaves implicit — enough to be useful, but 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 concrete verb and resource ('Returns 768-dimensional embedding vectors'), plus the batch ceiling (up to 50 texts) and the intended jobs (semantic search, clustering, deduplication). That makes it easy to separate from near-siblings like ai_classify or ai_sentiment, which return labels or scores rather than vectors.

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 three named use cases give an agent clear trigger conditions for choosing this over ai_chat or ai_summarize. It stops short of naming alternatives or stating when not to use it (e.g., single-text classification belongs to ai_classify).

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