Retrieve signal edges for a channel from a captured NPZ file: positions, times, and levels after each edge. Use pagination and filter by all, rising, or falling edges.
Paged edge listing for one channel: positions, times (s) and the level after each edge. kind: all | rising | falling.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | all | |
| limit | No | ||
| offset | No | ||
| channel | Yes | ||
| npz_path | Yes |
Changes observed during successful MCP inspections.
v2.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the behavioral burden. It discloses paging behavior, the kind filter, and the output content, but it does not mention ordering, failure behavior, read-only guarantees, or whether a file must already be loaded.
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 short sentences with no filler. It front-loads the core operation and output, then lists the kind values compactly.
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?
There is no output schema and no annotations, so the description is the main source of behavior. It provides the returned fields but omits prerequisites, ordering, and edge-case behavior, making it incomplete for an agent that must invoke this tool correctly in a larger workflow.
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 0% description coverage, so the description must compensate. It does clarify 'kind' with 'all | rising | falling', 'channel' via 'for one channel', and 'Paged' implies the purpose of limit and offset. However, npz_path and exact limit/offset semantics are still left implicit.
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 identifies the operation as a paged edge listing for a single channel and specifies the returned data: positions, times in seconds, and the level after each edge. It also distinguishes the edge-kind filter, which separates this from sibling tools like list_analyzers or measure_channel.
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 explains what the tool does but gives no guidance on when to use it instead of parse_file, measure_channel, capture, or list_analyzers. It also does not state prerequisites such as needing a parsed .npz file or an active connection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.