check_stability

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the resampling process, the computed metrics, the thresholds for flags, and notes that output size is small. It does not explicitly state that the operation is read-only, but it is implied as an analysis tool. The description adds meaningful behavioral context beyond a simple summary.

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 concise and well-structured, with a clear summary line followed by the key algorithm details. Every sentence adds value: it describes the process, the outputs, the thresholds, and the output size. No unnecessary content.

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?

The description covers the core algorithm, thresholds, and output size. With an output schema present, it does not need to detail return values. However, it lacks explicit guidance on when to use the tool compared to siblings, and could mention how it handles non-numeric or missing columns. Overall, it is complete for a moderately complex analysis tool.

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%, so the description must compensate for the lack of parameter documentation. It explains 'n_bootstrap' by describing the resampling count and relates 'columns' to 'numeric column'. However, 'source_id' is not explained, and the description does not clarify the default behavior when 'columns' is null. This partial compensation merits a middle score.

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 states the tool's purpose: 'Bootstrap stability of column means + signal-to-noise ratio (Level 6).' It specifies the verb (bootstrap/compute), the resource (column means) and the key outputs (bootstrap_std, CV, SNR), distinguishing it from sibling check_* tools like check_distributions or check_correlations.

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 implies usage for detecting unstable column means via CV>0.1 and low signal via SNR<1, but it does not explicitly state when to use this tool versus alternatives, nor does it mention exclusions or prerequisites. Usage is inferred from the tool's behavior rather than directly stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.