Katzilla MCP

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

Annotations provide readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=true, indicating safe, repeatable, and open-ended queries. The description adds valuable context beyond annotations: it specifies the data source (CMS, Public Domain), update frequency (quarterly), and the return format (Katzilla envelope with data, quality scores, and citation details like SHA-256 hash). This enhances transparency about data freshness, auditability, and output structure without contradicting annotations.

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 covers purpose, datasets, source, and updates; the second explains the return format and audit features. Every sentence adds value, with no redundant information, making it front-loaded and appropriately sized for the tool's complexity.

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 (3 parameters, annotations, and an output schema), the description is complete. It covers the purpose, data source, update frequency, and return format. With annotations handling safety and idempotency, and an output schema presumably detailing the Katzilla envelope, the description provides sufficient context without needing to explain return values or behavioral traits exhaustively.

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 input schema has 100% description coverage, with clear enum values and defaults for parameters like 'dataset' and 'state'. The description does not add significant meaning beyond the schema, as it only mentions the datasets generically (e.g., 'hospital quality ratings') without detailing parameter interactions or constraints. With high schema coverage, the baseline score of 3 is appropriate, as the description provides minimal extra parameter context.

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: it searches Medicare provider data from CMS, specifying the datasets (hospital quality ratings, nursing home inspections, physician comparisons, ACO performance) and the source. It uses a specific verb ('search') and resource ('CMS data catalog'), distinguishing it from sibling tools in the health category like 'health__cdc-data' or 'health__fda-recalls' by focusing on provider data rather than disease or regulatory information.

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 mentioning the data source (CMS), update frequency (quarterly), and the types of datasets available. However, it does not explicitly state when to use this tool versus alternatives (e.g., other health data tools like 'health__cdc-data' for disease data) or any prerequisites. The guidance is clear but lacks explicit exclusions or named alternatives.

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