post_embeddingsCreates an embedding vector representing the input text. Group: Embeddings. Billing per call: Credits: metered.
| Name | Required | Description | Default |
|---|---|---|---|
| body | No | JSON request body. Example: {"input":"Today is a wonderful day","model":"text-embedding-3-large"} |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It mentions the core effect (creating an embedding vector) and billing ('Credits: metered'), but does not disclose permissions, reversibility, or impact on resources. This is minimal transparency for a mutation 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 extremely concise: three short sentences that convey the purpose, group, and billing. No redundant information, and it is front-loaded with the primary action.
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 tool has moderate complexity (a nested object parameter) and no output schema. The description does not explain the return format or how to interpret the embedding vector, nor does it provide usage context beyond the basic action. This is inadequate for complete guidance.
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% (the 'body' property has a description with an example). The tool description adds no further parameter semantics beyond what the schema provides. Baseline 3 is appropriate since the schema handles the parameter documentation.
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 clearly states the tool's function: 'Creates an embedding vector representing the input text.' This is a specific verb+resource structure that distinguishes it from siblings like post_chat_completions and post_moderations.
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 description offers no guidance on when to use this tool versus alternatives. It mentions 'Group: Embeddings' but does not explicitly state when embeddings are appropriate or when to avoid it. No alternatives or exclusions are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool serves a completely distinct API endpoint: listing models, creating chat completions, generating embeddings, and moderating text. There is no overlap or ambiguity between the operations, making it clear which tool to select for a given task.
All tools follow a consistent verb_noun pattern using HTTP methods (get_ or post_) followed by the resource in snake_case (e.g., get_models, post_chat_completions). The naming is uniform and predictable.
With only 4 tools, the server is concise and well-scoped for its purpose of wrapping a core AI API surface. Each tool covers a fundamental operation (list, chat, embeddings, moderation) without unnecessary bloat.
The toolset covers the primary interactions with a typical AI API: listing models and generating completions, embeddings, and moderation scores. A minor gap is the lack of a single-model GET endpoint, but the current coverage handles core workflows effectively.