intervention_analysis

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

With no annotations provided, the description carries the full burden for behavioral disclosure. It transparently lists what the tool reports (e.g., extreme dates, variance fraction, affected lags, test reliability), but does not explicitly state whether it is read-only or if it modifies inputs. It also does not mention thresholds for flagging beyond the parameter, though the output list gives a clear sense of behavior.

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 well-organized with a one-line summary, a bulleted output list, and a parameters section. It contains no redundant text, though the output list is slightly long. Overall, every sentence contributes to understanding the tool's purpose and behavior.

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 diagnostic tool with no output schema, the description covers the main outputs and parameters effectively, listing exactly what will be reported. It lacks explicit statement of return format (e.g., console output vs. file) and does not explain whether the analysis is performed on an existing model or solely on the input file, but the core behavior is well documented.

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 description adds substantial meaning beyond the schema: it specifies that inp_path points to a .inp or .pre file and defines threshold as the |z| cutoff with a default of 3.5. This directly explains each parameter's purpose and format, compensating for the schema's lack of property descriptions.

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 opens with a specific verb and resource: 'Detect extreme residuals and assess their impact on ACF/PACF and tests.' This clearly states the tool's function and differentiates it from sibling tools like preliminary_outlier_scan (which likely scans raw data rather than residuals) and test_interventions (which likely tests intervention significance). The enumerated output items further clarify the scope.

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 does not explicitly state when to use this tool versus alternatives. It mentions 'residuals' which implies post-estimation, but there is no clear guidance on prerequisites, when an intervention analysis is needed, or which sibling tools (e.g., preliminary_outlier_scan) to use instead. The user must infer usage from the name and context.

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