Katzilla MCP

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

The description adds valuable behavioral context beyond the annotations. While annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=true, the description discloses that data 'updates daily' (freshness behavior) and specifies the return format as 'the Katzilla envelope { data, quality, citation }' with details about quality scores and citation content. This provides important operational context about data currency and output structure that annotations don't cover.

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 efficiently structured in two sentences: the first states the core purpose and scope, the second covers data source, update frequency, and return format. Every element serves a purpose, though the parenthetical '[Environment & Air Quality Agent]' adds little value and the detailed citation explanation could be slightly condensed. Overall, it's appropriately sized and front-loaded with essential information.

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?

Given the tool's moderate complexity (search with filtering), rich annotations covering safety and idempotency, 100% schema coverage, and existence of an output schema (implied by the return format description), the description is complete enough. It covers purpose, data scope, source, update frequency, and detailed return format—providing all necessary context for an agent to understand when and how to use this tool effectively.

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?

With 100% schema description coverage, the input schema already fully documents all 4 parameters (table, zipCode, state, limit) with descriptions, defaults, and enums. The description adds minimal parameter semantics by listing the specific table names in its opening sentence, but this largely repeats what's in the schema's table parameter description. The baseline score of 3 is appropriate when the schema does the 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?

The description clearly states the tool's purpose: 'Search EPA's Envirofacts multi-system database covering TRI facilities, RCRA hazardous waste, drinking water systems, Superfund sites, and air facilities.' It specifies the verb ('Search'), resource ('EPA's Envirofacts multi-system database'), and scope (listing specific database tables). This distinguishes it from sibling environment tools like EPA AQS or NOAA CDO that focus on different environmental data sources.

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 implies usage context by listing the database tables covered (e.g., TRI facilities, RCRA hazardous waste) and mentioning daily updates, suggesting it's for current environmental data queries. However, it doesn't explicitly state when to use this tool versus alternatives like EPA AQS (air quality) or EPA ECHO (compliance data), nor does it provide any exclusion criteria or prerequisites for usage.

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