validate_custom_modelValidate a developer-supplied model endpoint. Checks HTTPS, SSRF, and optionally probes the model with a minimal request. API keys are transient and never persisted or echoed.
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | ||
| probe | No | ||
| apiKey | No | ||
| baseUrl | No | ||
| authMode | No | bearer | |
| endpoint | No | ||
| adapterMode | Yes | ||
| promptField | No | prompt | |
| systemField | No | system | |
| apiKeyHeader | No | x-api-key | |
| responseTextPath | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as read-only and non-destructive, and the description adds meaningful behavioral detail beyond that: HTTPS and SSRF checks, an optional minimal probe, and the fact that API keys are transient and never persisted or echoed. This is strong safety-relevant disclosure, though it stops short of explaining failure behavior or probe side effects.
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?
Three sentences with no filler. The first sentence gives the core purpose, and the following two add high-value behavioral and security details. The description is front-loaded and every sentence earns its place.
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?
For a tool with 11 configurable parameters and no output schema, this description is too thin to support correct invocation. It provides a good orientation but not enough detail about required configuration or expected results.
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 schema has 11 parameters and 0% description coverage, so the description needed to clarify at least the key parameters. It mentions probe behavior and API keys conceptually, but it never names or explains critical fields like adapterMode, baseUrl, endpoint, authMode, promptField, or responseTextPath, leaving the agent to guess how to construct a valid call.
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 names a specific verb and resource: 'Validate a developer-supplied model endpoint.' It goes on to specify the concrete checks (HTTPS, SSRF, optional probe), which clearly differentiates this from sibling tools like run_custom_model or get_custom_model_capabilities.
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 intended use is implied: validate an endpoint before using it with a custom model. However, the description never explicitly states when to choose this over alternatives like run_custom_model or get_custom_model_capabilities, so the routing guidance is left to inference.
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.
Most tools are clearly separated by resource and action, but translate_text/localize_text and prepare_compare/prepare_custom_compare have adjacent purposes that could cause an agent to choose one when the other is intended. Descriptions provide enough distinction for a careful model, so the ambiguity is limited.
All 15 tools follow a consistent snake_case verb_noun pattern with verbs like build, detect, get, localize, open, prepare, run, search, transcribe, translate, and validate. There is no mixing of camelCase, vague imperative fragments, or generic action names.
15 tools is at the upper edge of a well-scoped set, and each functional area has dedicated tools. It is slightly heavy because a few pairs like translate/localize and prepare_compare/prepare_custom_compare are close variations, but the count is still reasonable for the server's broad workspace scope.
Core workflows are covered: template search/get/fill, translation and localization, custom model capabilities/validation/run, compare plan preparation, transcription, and entitlement checks. Gaps include no compare-plan execution tool, no template create/update/delete lifecycle, and no persistence for custom model configurations, but agents can work around these.