Send a generated test webhook to the user's localhost (the tunnel CLI must be running). Provide a provider (stripe, github, shopify, clerk, slack, resend, paddle, polar, lemonsqueezy) and optional event for a realistic sample payload, or pass a custom JSON body. Pro plan required.
| Name | Required | Description | Default |
|---|---|---|---|
| body | No | Custom JSON body (overrides the template) | |
| event | No | ||
| provider | Yes | ||
| subdomain | Yes |
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 indicate destructiveHint=true and openWorldHint=true, so the description adds value by disclosing the localhost target, the running tunnel CLI prerequisite, and the Pro plan requirement. It doesn't elaborate on side effects, but with annotations covering the safety profile, this additional context is meaningful and not contradictory.
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 two concise sentences. The first sentence states purpose and a key prerequisite; the second covers parameter options. No redundant words, and it is front-loaded with the action verb. Every sentence contributes.
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 description covers invocation context (tunnel, Pro plan), parameter options (provider list, event, body), and the target. However, it omits any description of the subdomain parameter and does not mention response format or error behavior, though no output schema exists. For a moderately complex tool, it is mostly complete but not fully.
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 coverage is low (25%), so the description compensates by enumerating valid provider values, explaining that 'event' provides a realistic sample payload, and clarifying 'body' as a custom override. However, the required 'subdomain' parameter is entirely unexplained in both schema and description, which is a significant semantic gap for a required field.
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 function: 'Send a generated test webhook to the user's localhost,' which is a specific verb+resource+target. It differentiates from siblings like get_request, list_requests, and replay_request by emphasizing generation and sending of a test webhook. The provider list adds concrete scope.
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 provides clear usage context by stating the prerequisite ('the tunnel CLI must be running') and explaining two usage modes: provider/event for realistic payloads or custom body. It doesn't explicitly exclude alternatives or name when not to use it, but the context is sufficient for an agent to decide when this tool is appropriate.
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.
Each tool has a distinct purpose: retrieving a specific request, listing requests, listing tunnels, replaying a captured webhook, sending a test webhook, and two separate configuration toggles. No semantic overlap exists, so an agent can reliably choose the right tool.
All tools follow a consistent verb_noun pattern in snake_case (e.g., get_request, list_tunnels, set_long_requests). The naming is uniform and predictable, making it easy to infer functionality from the name alone.
With 7 tools, the server is well-scoped for webhook tunnel management. Each tool addresses a clear need without redundancy or bloat, striking a good balance between functionality and simplicity.
The surface covers the core lifecycle: viewing tunnels, inspecting webhooks, replaying requests, generating test events, and configuring timeout/WebSocket behavior. Minor gaps include lack of tunnel creation/deletion or request cleanup, but these appear to be handled externally (via CLI) and do not hinder primary workflows.
