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

Annotations declare readOnlyHint=true, and the description adds substantial value beyond this: it specifies the data source (EPA AQS annual summaries), enumerates the returned fields, and explicitly states that unmonitored counties return null. This gives a clear behavioral profile without contradicting the 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 three sentences, efficiently covering what the tool returns, how to pass the parameter with examples, and the coverage limitation. No fluff or redundant information; it is well-structured and front-loaded with the tool's purpose.

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?

Given the tool's simplicity (one parameter, no output schema, read-only), the description is remarkably complete. It lists all expected return fields, explains the two acceptable input formats with examples, and discloses the null behavior for unmonitored counties. This is comprehensive for its complexity.

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%, as the parameter `county` already has a description in the schema. The tool description repeats the same format and examples, adding no new information beyond the schema. Per the rubric, a baseline of 3 is appropriate when the schema fully documents parameters.

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 provides county-level air-quality index from EPA AQS annual summaries and lists specific return fields (percentile rank, band, median AQI, % unhealthy days, p90 AQI). The phrase 'Returns' implies a retrieval action, and the focus on air quality distinguishes it from sibling tools like county_cancer or health_risk.

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 obtaining air-quality data by county and provides a coverage caveat ('Only EPA-monitored counties ... unmonitored counties return null'). However, it does not explicitly mention when to use this tool over alternatives or direct users to other tools for unmonitored counties, so guidance is implied rather than explicit.

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