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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: the material Superfund caveat (statewide returns because the EPA layer lacks county FIPS) is a significant non-obvious data-scoping behavior that an agent must know. The 'includes serving representative' note also adds useful context about response contents. The readOnlyHint aligns with the read-like nature described.

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 covering purpose, key exception, and contents. The first sentence front-loads the core purpose with specific scope, the second flags the critical Superfund behavioral caveat, and the third notes the representative inclusion. No wasted words, though the terse style could be slightly more structured. Efficient and information-dense.

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?

For a read-only profile tool with 100% schema coverage, clear purpose, and important behavioral caveats disclosed, the description is reasonably complete. It covers what data is returned, the scoping mechanism, the key exception (Superfund statewide), and the representative field. No output schema exists, so it can't lean on that, but the contents list partially compensates. Minor gaps: no mention of pagination, data freshness, or unit scales for toxic releases, but these are not critical for a profile tool.

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% with both parameters (stateCode and districtNumber) well-described in the input schema. The description adds the county-FIPS scoping detail that ties to the parameters conceptually but doesn't add syntax or format guidance beyond the schema. Baseline 3 is appropriate since the schema handles parameter documentation adequately and the description's FIPS mention adds some, but limited, additional meaning.

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 states a specific verb+resource ('Environmental profile for a congressional district') with clear scope delineation: regulated facilities, active violations, toxic releases, scoped by county FIPS. It distinguishes itself from sibling district-profile tools by specifying the environmental domain and clearly separates it from other get_district_* profiles.

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 implicit usage context: this tool returns district-scoped environmental data. It clarifies the important exception that Superfund sites are returned statewide rather than per district, which is a key behavioral distinction. It doesn't explicitly name alternatives (e.g., search_epa_facilities for raw facility queries), but the statewide caveat provides meaningful guidance about scope expectations.

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