embeddings_contextualized

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

The description explains the core behavioral trait (contextualization) and the input structure. However, with no annotations, it leaves gaps about output format, error behavior, and any restrictions (e.g., number of chunks). It does not explicitly state whether this is a read-only operation.

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?

Three sentences, each with a distinct role: purpose, differentiation, input syntax. No fluff.

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?

The description is sufficient for a reader to understand the tool's purpose and how to structure input. However, it omits any mention of return values or how the embeddings are associated with chunks, which would be helpful given no output schema.

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 covers 100% of parameters with descriptions. The description adds the high-level structure ('each inner array is a document's chunks') which is already present in the schema. It does not add new details 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?

The description uses the verb 'Generate' with a specific resource ('context-aware embeddings for document chunks') and explicitly contrasts with 'standard embeddings', distinguishing it from the sibling tool 'embeddings_create'. The endpoint reference adds specificity.

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 states the tool is for context-aware embeddings where chunks are influenced by surrounding chunks, producing better representations for RAG. This implies the use case (RAG) and contrasts with standard embeddings, but it does not explicitly name alternative tools or give when-not-to-use guidance.

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