Checks a single training run for missing final eval, NaN/inf loss, loss spikes, early stopping, or too many Gaussians to explain failures or missing results.
Check one run for problems: missing final eval, NaN/inf loss, loss spikes, stopping early, too many Gaussians. Use it to explain why a run failed or has no results.
| Name | Required | Description | Default |
|---|---|---|---|
| run | Yes | Run name exactly as returned by list_runs, e.g. 'lego_baseline'. |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the behavioral load. It does disclose the concrete diagnostic categories it evaluates, which is useful, but never states that it is read-only, what the report/return shape looks like, or how expensive the check is — meaningful gaps for an unannotated tool.
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?
Two sentences: the check list is front-loaded and the purpose clause follows. Every phrase carries information; no filler.
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 single-parameter read diagnostic with no output schema, the description covers what is inspected and why you'd call it. The main remaining gap is what the result actually looks like (issue list? pass/fail summary?), which matters slightly more given no output schema exists.
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 100% and the schema already explains the run name with an example ('lego_baseline'). The description adds no further parameter semantics, so the baseline 3 applies.
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?
States a specific verb ('Check') applied to a specific resource ('one run') and enumerates the exact conditions it looks for (missing final eval, NaN/inf loss, loss spikes, early stopping, too many Gaussians). This clearly separates it from list_runs, compare_runs, get_metric_curve and other siblings.
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?
'Use it to explain why a run failed or has no results' gives a concrete triggering condition. It stops short of naming alternatives or exclusions (e.g., when to prefer compare_runs or get_final_metrics), so it is clear context without explicit routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.