post_chat_completionsCreates a model response for the given chat conversation. Group: Chat. Billing per call: Credits: metered (~0 avg).
| Name | Required | Description | Default |
|---|---|---|---|
| body | No | JSON request body. Example: {"model":"gpt-5-mini","stream":false,"messages":[{"role":"user","content":"How many days in 3 weeks."}]} |
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 only adds 'Group: Chat' and billing metadata; it does not describe response behavior, potential side effects, authentication needs, rate limits, or streaming implications. 'Creates a model response' is a minimal functional statement, not transparency.
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 compact and front-loaded with the core purpose. The addition of 'Group: Chat' and billing info is brief, though not strictly necessary, making it slightly less lean than ideal but still efficient.
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 no output schema, yet the description does not explain what the model response will look like, what fields in 'body' are required, or how to handle streaming. The embedded example in the schema provides partial guidance, but the overall description is incomplete for a tool of this complexity.
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% for the single 'body' parameter, and the schema includes an example JSON payload. The tool description itself adds no parameter-level meaning, so the baseline of 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?
Description clearly states it 'Creates a model response for the given chat conversation,' using a specific verb and resource. This distinguishes it from siblings like get_models, post_embeddings, and post_moderations, which address different endpoints and purposes.
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 phrase 'for the given chat conversation' provides clear context that this tool is for chat-completion requests. However, it does not explicitly mention when not to use it or point to alternatives, stopping short of a perfect score.
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.