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

Beyond the read-only, open-world, non-destructive annotations, the description discloses important behavior: 1024-dimensional multilingual output, batch limits, pricing, x402/USDC payment, and that failed calls are not charged. These are exactly the kind of operational and cost details an agent needs before invoking the tool.

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?

The description is a single dense sentence with no wasted clauses: model, dimensionality, use cases, limits, cost, payment rail, and failure policy are all front-loaded and relevant.

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 one-parameter tool with full schema coverage and annotations, the description covers the key operational facts: model, output dimensionality, batch and text limits, cost, and payment behavior. It does not explicitly describe the response structure, but the mention of 1024 dimensions makes the return shape largely inferable.

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 coverage is already 100% for the single 'texts' parameter, establishing a baseline of 3. The description adds value beyond the schema by specifying the per-call batch limit and an 8,000-character per-text limit, though it does not explain ordering or edge-case handling for empty strings.

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, 'Text embeddings', identifies the model and dimensionality (BGE-M3, 1024 dimensions), and names concrete use cases (search, clustering, RAG). This is enough for an agent to distinguish it from generation, summarization, translation, and retrieval-adjacent siblings.

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?

It gives clear usage context by naming search, clustering, and RAG as intended applications. It does not explicitly say when to prefer a sibling or when not to use embeddings, so it falls short of full alternative-routing guidance.

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