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

With no annotations, the description carries the full burden and does substantial work: data vintage (EPA 1993 map, lab data 2008-2017, CDC latest year), the ZIP-to-multiple-counties-by-land-share expansion, the Pennsylvania ZIP-level DEP exception, and the return value (county page URL). What it omits is failure behavior — required parameters are 0 in the schema, so an agent is not told what happens if neither address nor ZIP is supplied, or if an address cannot be resolved to a county.

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?

Front-loaded with the two deliverable values (zone and test results) before the source citations, which is the right order. The parenthetical inventory of state data sources (New York DOH, Pennsylvania DEP, Tennessee DOH) is the least essential part and inflates the block without changing how the tool is called.

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?

No output schema exists, so the description must convey returns; it names the county page URL but does not enumerate the response fields beyond the statistics mentioned inline. Combined with the data-vintage and geographic-expansion disclosure, this is enough to call correctly, though the shape of the returned statistics is only lightly sketched.

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, and it does: address is spelled out as house number, street, city, state, and zip_code as a 5-digit ZIP. It also explains the semantic consequence of each choice (ZIP fans out to every overlapping county by land share, plus ZIP-level PA DEP results). It stops short of saying whether both may be supplied together or which wins.

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?

States a specific verb and resource: returns the EPA radon zone plus county test statistics for a US street address or 5-digit ZIP. The input modality (address/ZIP rather than county/state) is what separates it from siblings like radon_by_county and radon_state_summary, and that distinction is stated up front.

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?

'Give `address` (house number, street, city, state) OR `zip_code`' gives explicit input guidance, and 'Not a radon measurement of any building' sets a clear expectation boundary. It never names radon_by_county or radon_state_summary as the alternative when the user already knows the county, so routing between the three radon tools is left to inference.

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