diagnose_result

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

Annotations only carry readOnlyHint=true and openWorldHint=false. The description goes far beyond this by disclosing the auto-selection logic, the assumption that result carries method_type, the validity condition for sub-checks, the use of alpha as significance threshold, and the fact that p-values are not multiplicity-corrected. It also exposes failure modes, including empty 'checks' for unrecognized methods. This is rich behavioral disclosure with no contradiction.

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 long but well-structured with labeled sections (Assumptions, Pre-conditions, Failure modes, Alternatives, Typical minimum N). The core purpose is front-loaded in the first sentence, and every section adds operational value for a complex router tool. No filler or repetition.

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 complex diagnostic router with 7 parameters, an output schema, and many siblings, the description covers purpose, assumptions, pre-conditions, failure modes, alternatives, and a typical minimum N. The output schema exists, so return values need not be spelled out. The description leaves little an agent would need to ask about.

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 provides detailed descriptions for all seven parameters (e.g., detail payload depths, data_path formats, as_handle caching). The description adds no parameter-specific meaning beyond the schema; it mentions 'supplied alpha' but alpha is not a parameter in the schema. Baseline 3 is appropriate.

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 states a specific purpose: a method-aware diagnostic battery that auto-selects tests by model type (OLS/DID/RDD/IV/SCM). It clearly identifies the resource (fitted result object) and the action (diagnostics), but does not explicitly distinguish itself from sibling tools like diagnose, assumption_audit, or forest_diagnostics, leaving some differentiation to inference.

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 provides concrete context: pre-conditions (fitted estimator with exposed internals), failure modes (raw data or unrecognized method type), and explicit alternatives (unified_sensitivity, sensemakr, oster_bounds, spec_curve). It tells the agent to run a standalone diagnostic when the method type is unrecognized, which is a clear when-not. It doesn't give a crisp positive selection rule beyond being a router, but the guidance is solid.

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