epa_air_quality

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

Annotations already provide readOnlyHint=true, and the description is consistent with that (no contradiction). Beyond the annotation, it adds valuable behavioral context: mandatory auth credentials with signup URL, the same-year date constraint, zero-padded FIPS codes, and what kind of data is returned. It does not cover pagination, rate limits, or error modes, but with the read-only annotation covering the safety profile, the added context earns a 4.

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 a single dense, front-loaded paragraph with no filler, but roughly half of it duplicates the input schema: the parameter code list, the service list, and the FIPS examples all appear again in the property descriptions. The auth and date-constraint sentences earn their place, but the redundancy keeps it from being zero-waste.

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?

With 6 parameters, no output schema, and nontrivial service options, the description covers all major decision points: which service to select, which pollutant code to pass, date formatting and same-year restriction, and required credentials. It partially states what is returned ('county-level monitor readings') but omits pagination, response structure, and failure behavior, leaving it just short of a 5.

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 each property is already richly documented — param codes with pollutant names, date format and same-year rule, FIPS examples, service list with defaults, and county examples. The description largely restates this schema content rather than adding new meaning, so it stays at the baseline 3; the only genuinely new information (API key/email requirement) is tool-level, not parameter-level.

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+resource pair — 'Get air quality data from EPA's Air Quality System (AQS)' — and further clarifies scope with 'county-level monitor readings for criteria pollutants' plus the service list. It does not explicitly distinguish itself from sibling `epa_aqs_daily`, and the first sentence's 'annual summary data' slightly undercuts the wider service range (daily/quarterly/sample), so it misses the top score.

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 gives concrete when/how-to-use guidance: it explains how to choose among annual, daily, quarterly, and raw sample services; states that bdate/edate must be in the same year in YYYYMMDD format; documents 2-digit FIPS state codes with named examples; and flags the AQS_API_KEY/AQS_EMAIL credential requirement with a signup link. It does not mention when NOT to use it or name alternatives, so it lacks explicit exclusions.

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