create_embeddingsConverts text into vector embeddings using a specified OpenAI model, enabling semantic search, clustering, and similarity comparison.
Get vector embeddings for one or more pieces of text
| Name | Required | Description | Default |
|---|---|---|---|
| input | Yes | Text (or array of texts) to embed | |
| model | Yes | OpenAI model to use for embeddings |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare readOnlyHint=true, and the description adds nothing beyond that. It says nothing about cost per token, which model is appropriate, batch size limits, whether embeddings are deterministic, or how many vectors come back for an array input — all real concerns for an embedding call.
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?
A single front-loaded sentence with no filler. It is terse to the point of under-specification, but nothing in it is wasted.
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?
There is no output schema, so the description should explain what comes back (embedding vectors, one per input, fixed dimensionality). It also gives no guidance on model selection even though 'model' is required. For a required-parameter tool with no output contract, this leaves meaningful gaps.
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 'input' and 'model' are already documented. The description's phrase 'one or more pieces of text' echoes the schema's anyOf without adding format, size, or model-choice guidance, so 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 specific verb+resource ('Get vector embeddings') and notes it accepts one or many texts, which is enough to distinguish it from all siblings (text/image/audio generation). It stops short of naming why an agent would pick this over, say, generate_text, but the resource is unambiguous.
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?
There is no statement of when to use this tool, when not to, or what the alternatives are. The agent is left to infer that this is for semantic search / similarity / clustering use cases rather than text generation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.