Skip to main content
Glama

测试引擎连接或重新检测 Codex

app_test_provider

Tests AI provider connectivity by re-probing a local Codex CLI executable or sending a minimal request to an OpenAI-compatible base URL, returning latency or error details.

Instructions

UI 专用:provider=codex-cli 时异步重新探测本机 codex.exe;provider=openai-compatible 时向 Base URL 发最小化探测请求返回延迟或错误。

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "app_test_provider"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNo
apiKeyNo
baseUrlNo
providerNo
clearApiKeyNo
customCodexPathNo
existingPersonaIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, and it does disclose the important behavioral trait: the codex-cli branch is asynchronous (fire-and-forget), while the openai-compatible branch performs a live minimal network call and returns latency or an error. That distinction is exactly what an agent needs to know. It stops short of saying whether credentials are required for the probe or what happens to existing state.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single semicolon-delimited sentence that leads with the scope qualifier and then branches by provider value — dense but front-loaded and free of filler. It borders on being too compressed, since the terse clause structure pushes detail onto the reader.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The return behavior (latency or error) is described, which matters given there is no output schema, and the async-vs-sync split is covered. Against 7 parameters, zero annotations, and no required fields, though, the description leaves too much of the parameter surface unexplained for an agent to configure the call confidently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 7 parameters, so the description must compensate and largely does not. It explains only `provider` and `baseUrl` (plus implicitly `customCodexPath` via 'codex.exe'), leaving `model`, `apiKey`, `clearApiKey`, and `existingPersonaId` completely undocumented in both schema and prose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names concrete actions — asynchronously re-probing the local codex.exe, or sending a minimal probe request to Base URL — so the resource (engine connectivity) and verb (probe/test) are identifiable. It doesn't restate the tool name and cleanly separates the two provider modes, but the overall goal ('test connection') is implied rather than stated outright.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

"UI 专用" scopes it to UI use, and the provider-conditional branches hint at which mode applies to which configuration. However, there is no explicit when-to-use vs. when-not-to-use guidance, no prerequisites (e.g., an API key must already be configured), and no mention of any sibling or alternative approach.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.