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

The annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), so the description's added value is the query-breadth rejection rule and the hint about which result field feeds other tools — neither of which is encoded in structured data. It stops short of disclosing pagination behavior or what a truncated/rejected response looks like.

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?

Three tight sentences ordered purpose -> return payload -> usage constraint, with zero filler. The most decision-relevant constraint (breadth rejection) is placed where an agent will hit it before constructing a call.

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 no output schema, the description correctly compensates by enumerating the returned fields (Registry ID, address, compliance snapshot across CAA/CWA/RCRA/SDWA), and it covers the required-filter constraint. It leaves the result-count/pagination behavior implicit, which is a minor gap for a list endpoint.

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%, so every parameter is already documented with examples and bounds (limit max 100, zip format, state code format). The description restates the filter set at a high level but adds no syntax, precedence, or combine-semantics (e.g. whether city+state are ANDed) beyond the schema. Baseline 3 applies.

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 ('Search EPA-regulated facilities') plus the exact filter dimensions (state, city, zip, name) and what comes back (Registry ID, address, compliance snapshot). The note that the Registry ID is 'needed for the other EPA tools' implicitly separates this entry-point lookup from epa_facility_details, epa_facility_compliance, and epa_enforcement_search.

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?

Gives a clear precondition ('Provide at least one filter') and a concrete failure mode with remediation ('broad queries ... may be rejected as too broad, so add a city, zip, or name'). It does not, however, explicitly name the downstream alternatives (e.g. epa_facility_compliance) for once a Registry ID is in hand, so it stops one step short of full when/when-not routing.

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