List requests captured by a bin, oldest first. Compact summaries (id, method, path, time, content-type, body size, signature status). Use get_capture for full headers/body. Pass after (a capture id) to only see newer captures.
| Name | Required | Description | Default |
|---|---|---|---|
| bin | Yes | bin id (or custom slug) from create_bin | |
| after | No | only captures with id greater than this (default 0) | |
| limit | No | max results, 1-50 (default 20) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
There are no annotations, so the description carries the full burden of behavioral disclosure. It does well by stating the ordering (oldest first), the summary fields returned, and the filtering behavior of 'after.' This is more transparent than a minimal description, though it does not detail error cases or potential side effects, which are unlikely for a list operation.
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 main purpose is front-loaded, followed by the summary format, the routing to get_capture, and the 'after' parameter behavior. 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?
Even without an output schema, the description identifies the key return fields, making the output format clear. It also points to the tool for full details when needed. Combined with a fully documented schema, the definition is complete for an agent to invoke correctly.
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 already documents all three parameters with 100% coverage, so the baseline is 3. The description adds a brief explanation of 'after,' but it largely restates the schema's meaning, adding little new semantic value.
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 starts with a specific verb and resource: 'List requests captured by a bin, oldest first.' It also differentiates itself from get_capture by noting it returns compact summaries rather than full headers/body, so an agent can distinguish it from its sibling tools.
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 explicitly says 'Use get_capture for full headers/body,' giving a clear condition for choosing the alternative tool. It also implies when list_captures is appropriate: when compact summaries are sufficient.
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 targets a distinct action—create bin, read/list/wait for captures, simulate a delivery, configure a response, and verify a signature. The reading tools are differentiated by listing summaries vs. retrieving full captures vs. blocking for the next arrival, so agents should not misselect.
All tool names follow a consistent lowercase snake_case verb_noun pattern: create_bin, get_capture, list_captures, set_response, verify_signature. Multi-word targets and wait_for are still predictable and match the same imperative style.
Seven tools cover the webhook capture workflow without redundancy or bloat. Each tool serves a concrete stage in the create → capture → inspect → respond → verify loop, which is an ideal scope for an MCP server.
The core lifecycle is well covered: bins can be created, captures can be listed/read/waited for, test webhooks can be generated, responses configured, and signatures verified. Minor gaps exist around bin lifecycle management—there is no list_bins/get_bin/delete_bin or capture deletion—but auto-expiring anonymous bins make this a workable, not blocking, omission.