Retrieve buffered runtime console errors, uncaught exceptions, React hydration errors, and failed network requests from the active dev page to debug without manual copy-pasting.
Retrieve buffered runtime console errors, uncaught exceptions, React hydration errors, and failed network requests from the active dev page without manual copy-pasting.
| Name | Required | Description | Default |
|---|---|---|---|
| level | No | errors-only | |
| limit | No | ||
| clearAfterRead | No |
Changes observed during successful MCP inspections.
v0.17.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It does add useful behavioral context by saying the data is 'buffered' and comes 'from the active dev page', implying persistence until cleared and a session dependency. However it omits whether reads are non-destructive by default, buffer size/cap behavior, and any auth or connection requirements.
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?
A single front-loaded sentence with the verb and content types first. The trailing 'without manual copy-pasting' is mild marketing filler rather than specification, but the whole remains tight and readable.
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?
No annotations and no output schema mean the description must stand alone, yet it does not describe return format, ordering, buffer semantics, or how the three parameters shape results. For a telemetry-retrieval tool with three undocumented parameters, this leaves significant gaps.
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 0% for all three parameters. The description's enumeration of error categories loosely maps to the 'level' enum (all/errors-only/warnings-and-errors) but never mentions 'level', 'limit', or 'clearAfterRead', so the two most consequential parameters are undocumented in both schema and prose.
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 uses a specific verb ('Retrieve') and enumerates the exact resource: buffered console errors, uncaught exceptions, React hydration errors, and failed network requests. This is much clearer than a generic 'get telemetry', though it never explicitly names or contrasts the sibling vibeside_telemetry_clear that a caller must also consider.
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?
There is no when-to-use guidance, no prerequisites (e.g., an active dev page / connected session), and no mention of alternatives such as vibeside_hmr_telemetry, vibeside_observe_long_tasks, or the sibling vibeside_telemetry_clear. The agent must infer the debugging scenario entirely.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.