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

The description adds substantial behavioral detail beyond the annotations: it fetches real data, performs lock-in detection with a local-background null and a positive control, returns UNTESTABLE if the reference line is not recovered, and distinguishes synthetic demo vs. live authenticated modes. This is rich, specific behavioral disclosure with no contradiction to 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?

The description is information-dense and mostly front-loaded with the key purpose. Some promotional phrasing ('honest verdict it cannot fake', 'Lab-as-an-API') is not strictly necessary, but the structural content about controls, tiers, and recipe earns its place.

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 tool with no output schema, the description gives adequate context on methodology, control behavior, and tier availability. The main gaps are unspecified return-value structure and minimal guidance on parameter selection (especially lat/lon/window_days), but the overall operational context is strong.

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 only 50%, and the description does not meaningfully clarify lat, lon, window_days, or hypothesis beyond what the schema states for carrier and observable. It indirectly references carrier via the positive control line but leaves core parameters underspecified for an agent selecting values.

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 a specific verb and resource: 'run a REAL, bounded controlled test at a location' and get a verdict. It distinguishes this tool from generic 'verify' siblings by emphasizing the lab-as-an-API methodology with positive/negative controls, though it does not explicitly name sibling alternatives.

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 explains when the tool is appropriate — when a grounded, cannot-fake controlled test is needed — and notes free vs. authenticated tiers. However, it does not explicitly state when not to use it or how it compares to sibling tools like check_hypothesis, verify, or ground_truth.

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