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

Annotations already cover the read-only, idempotent, non-destructive safety profile. The description adds genuine behavioral context beyond annotations: broad queries may be rejected, at least one filter is required, and the return payload covers Registry ID, address, and a multi-program compliance snapshot. No contradiction with the readOnlyHint.

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 sentences, each earning its place: the core action, the return value with downstream relevance, and the filter/query-construction constraint. Everything is front-loaded with no filler or redundancy.

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 appropriately carries the return-value burden by listing Registry ID, address, and the compliance programs covered. It also discloses rejection behavior and the filter requirement. Slightly shy of a 5 only because it omits minor details like result ordering or the behavior of name-fragment matching.

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 coverage is 100%, so each of the six parameters is already documented in the input schema. The description adds a cross-parameter constraint not captured in the schema (at least one of state/city/zip/name must be provided) and warns against overly broad combinations, which is useful but modest on top of the schema's heavy lifting.

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 ('Search') and resource ('EPA-regulated facilities'), enumerates the filter dimensions, and details the return payload. The mention that Registry ID is 'needed for the other EPA tools' positions this as the entry point to the EPA tool family, distinguishing it from detail/compliance-oriented siblings like epa_facility_details.

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 concrete, actionable usage conditions: 'Provide at least one filter' and warns that broad queries like state-only for a large state 'may be rejected as too broad.' This is clear context for constructing valid calls. However, it never names sibling alternatives or explicit when-not-to-use conditions (e.g., 'use epa_facility_details once you have a Registry ID'), so it stops short of a 5.

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