Skip to main content
Glama
Better Mealie MCP

Better Mealie MCP

Create Groups Ai Providers Providers By Provider Test

create_groups_ai_providers_providers_by_provider_test

Tests connectivity for a saved AI provider with optional unsaved edits, letting you verify changed model or base URL settings before saving.

Instructions

Test connectivity for an already-saved provider.

Accepts optional unsaved edits to test against instead of what's in the database - e.g. while editing a provider, the caller may have changed the model/base_url but left the API key blank (meaning "keep the existing one"), so a plain "unsaved" test can't be used since it has no way to supply that key. The saved key and header/param values are only used while the base URL is unchanged; otherwise the caller must supply new ones.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "provider_id": "<provider_id>"
    },
    "name": "create_groups_ai_providers_providers_by_provider_test"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyNo
provider_idYes
accept-languageNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv3.27.0

TDQS

A3.8/5.0
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 discloses a genuinely non-obvious behavioral rule: saved key/header/param values are reused only while the base URL is unchanged; otherwise the caller must supply new credentials. That is real value beyond the schema. It still does not say whether the call has any side effects (persisting the submitted edits?), whether it consumes provider quota, or how failures surface.

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?

Purpose is front-loaded in the first sentence, with the rationale following in a clearly separated paragraph. The second paragraph is dense and slightly circular ("a plain 'unsaved' test can't be used since it has no way to supply that key"), but every clause carries information about credential fallback that an agent needs.

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?

An output schema exists, so return values need not be described, and the credential-fallback rule is covered. However, for an un-annotated tool with 0% schema description coverage, the description omits side-effect/persistence behavior and leaves most body fields undocumented, so an agent still has gaps before calling it correctly.

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

Parameters3/5

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

Schema description coverage is 0% across three parameters with a nested body of seven fields, so the description must compensate. It does explain the semantics of a blank apiKey ("keep the existing one") and touches on model/baseUrl, but leaves name, timeout, requestParams, requestHeaders, provider_id and accept-language entirely unexplained. Partial compensation only.

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?

"Test connectivity for an already-saved provider" gives a specific verb (test) and resource (provider connectivity), and the qualifier "already-saved" separates it from the sibling that tests an unsaved provider. It never names that sibling, but the phrase "a plain 'unsaved' test" makes the distinction readable without opening the other schema.

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

Usage Guidelines4/5

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

The second paragraph sets out the exact condition that selects this tool: the provider exists in the database but the caller has pending edits (e.g. changed model/base_url, blank API key). It also states implicitly when not to use it by explaining why the unsaved-test variant fails for that case. The guidance is clear but the alternative tool is never named, so an agent must match it against the sibling list itself.

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

Deploy Server

Other Tools