GPT-4o: GPT-4o (“o” for “omni”) is our versatile, high-intelligence flagship model. It accepts both.
Scored across 1 tool
With only one tool, there is no possibility of ambiguity between tools. The agent will always select the correct tool because there is exactly one available.
The single tool follows a verb_noun pattern (post + chat_completions), which is consistent and readable. However, 'post' is less standard than 'create' for this action, but it is not confusing.
A server with only one tool feels extremely thin. Even for a single-purpose API, one tool is usually insufficient to support meaningful agent workflows, as the guidelines note that 1-2 tools are borderline but typically inadequate.
The tool surface is severely incomplete for a chat completion API. It lacks model listing, streaming support, or any management endpoints, making it impossible for an agent to perform basic discovery or handle common variations.
Creates a model response for the given chat conversation Billing per call: Credits: metered.
| Name | Required | Description | Default |
|---|---|---|---|
| body | No | JSON request body. Example: {"model":"GPT-4o","stream":false,"messages":[{"role":"user","content":"There are ten birds in a tree. A hunter shoots one. How many are left in the tree?"}]} |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that billing is metered, which is useful, but it does not mention side effects, safety, throttling, or error behavior. It also fails to clarify that it is a non-mutating generation call beyond the verb 'creates'. Minimal disclosure beyond cost.
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 short and gets to the point. However, the billing note is awkwardly appended and could be better structured. It is still concise and front-loaded with the purpose, so it earns a 4.
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?
With no output schema, the description should explain what the response looks like, but it does not. It also lacks guidance on expected behavior for streaming or formatting. Given the tool's simplicity (one param) and lack of annotations, the description is incomplete for an agent to fully understand the tool's usage and output.
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, which includes a detailed example. The tool description adds 'chat conversation' context but essentially repeats what the schema already conveys. Baseline 3 is appropriate since the schema does the heavy lifting.
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 'Creates a model response for the given chat conversation', which is a specific verb+resource. It distinguishes itself from nothing since there are no siblings, but it is clear enough. It could be more explicit about being the chat completions endpoint, but the title and context make it 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?
The description implies it is used for chat conversations, but provides no explicit guidance on when to use it versus alternatives. Since there are no sibling tools, this is acceptable but still lacks any exclusions or prerequisites. The billing note is not a usage guideline.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
post_chat_completionsGPT-5: GPT‑5 is OpenAI’s most advanced and unified AI model, combining fast, real-time.
Swift AI: Access a wide range of AI models⚡, including OpenAI 🤖,DeepSeek 🔍, Claude 🧠, Gemini 🌟, and.
GPT, Claude, Gemini, DeepSeek, Grok, Qwen and GLM through one API key. Pay per token.
AI model releases, price changes and deprecations in one feed: chat, embedding, speech, video.
Add one secure layer between your agents and this server.