Checks finite samples, signal quality, and GWOSC flags for a detector run, then returns an evidence ID for traceable data-quality review.
Check finite samples, signal quality and GWOSC flags; returns evidence ID.
| Name | Required | Description | Default |
|---|---|---|---|
| run_id | Yes | ||
| detector | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description's "returns evidence ID" usefully explains why readOnlyHint is false — the call persists an evidence artifact even though the operation reads like a check. It does not say what a failed check looks like, whether a low-quality verdict raises an error, or whether the evidence record is immutable, so it only partially adds beyond the annotations.
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 compact sentence with the check targets front-loaded and the return-value clause trailing. No filler, though the terseness tips into under-specification rather than true conciseness.
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 two-required-parameter tool with no output schema and no parameter documentation, the definition is thin: GWOSC flags and "finite samples" are unexplained domain terms, and neither the failure semantics nor the evidence-ID lifecycle is covered. Adequate as a pointer, insufficient as a spec.
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 description coverage is 0% for two required parameters, so the description must carry the burden and does not: no hint about run_id format, valid detector identifiers (e.g. H1/L1/V1), or case sensitivity. An agent could easily pass an invalid detector string.
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?
Uses a specific verb ("Check") with three named resource types — finite samples, signal quality, GWOSC flags — plus the side effect of returning an evidence ID. That is enough to distinguish it from siblings like analyze_detector or verify_artifacts, though it never explicitly names which sibling covers the adjacent case.
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?
No guidance on when to run this check, whether it must precede fetch_strain or analyze_detector, or what to do with the returned evidence ID. The agent must infer workflow placement from the sibling list alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.