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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds valuable behavioral context by listing the exact return fields (violation code, health-based flag, contaminant code, etc.) and the data source. It doesn't mention pagination or open-world behavior, but the annotation covers the latter.

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 about five sentences, each serving a purpose: function, return fields, filter guidance, category enumeration, sibling pointer, and data source. It's slightly longer than necessary but remains digestible and well-structured, with the core function front-loaded.

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?

The description covers the tool's purpose, parameters, filtering semantics, sibling relationship, and data provenance. With the schema fully documenting parameters and an output schema present, the description is largely complete. Minor gaps like pagination behavior are not mentioned, but the annotations and schema fill most functional needs.

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?

The schema has 100% coverage with descriptions for all four parameters, so the baseline is 3. The description adds extra semantic value by explaining the health_based filter's effect (focus on MCL/TT, direct public health endangerment) and listing the violation categories, which goes beyond simply repeating the schema's parameter descriptions.

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 and resource: 'Search EPA SDWIS for drinking water violations by state and violation type.' It clearly distinguishes itself from the sibling sdwis.water.enforcement by stating when that sibling should be used instead, giving agents a precise scope and differentiation.

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 explicitly provides usage context: filtering by health_based=true to focus on MCL/TT violations, and directing the agent to sdwis.water.enforcement for enforcement actions. This tells the agent when to use this tool and when to use an alternative, leaving little to inference.

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