GPT-5: GPT‑5 is OpenAI’s most advanced and unified AI model, combining fast, real-time.
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Average 3.2/5 across 1 of 1 tools scored.
Only one tool exists, so there is no possibility of selecting between overlapping tools. The purpose of post_chat_completions is unambiguous.
With a single tool, naming consistency is not at risk. The name follows a clear snake_case verb_noun pattern and accurately describes the action.
A single tool feels thin for a server named gpt-5, which could plausibly expose model listing or other variants, but it does cover the core chat completion operation without redundancy.
The tool covers the primary chat completion call completely for a stateless API. Minor gaps such as streaming or model discovery are not exposed, but no dead-end workflows exist for the stated purpose.
post_chat_completionsChat CompletionsBInspectCreates 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-5","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 of behavioral disclosure. The description only notes that billing is metered per call, providing some transparency about cost, but it does not disclose other behavioral traits such as whether the response can be streamed (though the example includes 'stream': false), whether there are rate limits, or any side effects. Since it is a creation call, one might assume it is not read-only, but the description does not explicitly state any mutation or persistence. The metering note is a plus but not sufficient for full 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 concise, consisting of one clear sentence followed by a billing note. It is front-loaded with the main purpose and includes an additional detail about billing. There is no unnecessary verbosity, and the structure is straightforward.
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 is relatively simple with a single parameter, and the schema provides a full example. However, there is no output schema, and the description does not explain what the response looks like or any error conditions. While the agent might infer that the response is the model's completion, the description could be more complete by mentioning the return format, especially since the tool's name 'post_chat_completions' suggests a REST API that typically returns the generated response. Without output schema, the description should at least hint at the output nature.
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?
The input schema has one parameter, 'body', which is fully described with a detailed example. The schema description coverage is 100%, meaning the schema itself provides the necessary semantics for the parameter. The description adds a billing note but does not elaborate further on the parameter's structure beyond what the schema already offers. Since the schema covers the parameter thoroughly, the baseline score of 3 is appropriate.
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 purpose: 'Creates a model response for the given chat conversation.' It specifies the verb (creates), the resource (model response), and the context (chat conversation). Although no sibling tools are provided for differentiation, the purpose is specific enough for an agent to understand its core function.
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 when to use this tool: when generating a model response for a chat conversation. However, it does not provide explicit usage context, such as requirements for the 'body' parameter, expected message format, or any alternatives. Given the simple scope, the implied usage is adequate but lacks explicit guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
No comments yet. Be the first to start the discussion!