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

Annotations cover the safety profile, and the description adds non-obvious operational facts the annotations cannot: per-call billing at $0.003 via x402 USDC or card key, failed calls are free, and repeats are charged (reinforcing idempotentHint=false). That is exactly the context an agent needs before calling.

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-loads the output shape and model, then use cases, then an example, then pricing and safety. Dense but every sentence carries distinct, actionable information with no 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 single-parameter, no-output-schema tool, the description covers the return artifact (1024-dim vector), input limits, use cases, cost, and side-effect profile. Nothing needed to call it correctly is missing.

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% with a single well-documented 'text' parameter, so the schema carries the burden. The description restates the 4,000-character limit and adds an example value, but contributes no syntax or format detail beyond the schema.

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?

Names a specific operation and artifact – a 1,024-dimension embedding vector from BAAI's BGE-M3 for up to 4,000 characters in 100+ languages. This is instantly separable from sibling text tools like ai_chat, ai_classify, and ai_summarize_text.

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?

Explicitly lists intended uses (semantic search, RAG retrieval, clustering, deduplication) and gives a concrete example call. It does not name when to prefer a sibling (e.g., ai_chat for free-form generation), so it stops short of full routing guidance.

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