Katzilla MCP

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

Annotations already provide readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=true. The description adds valuable behavioral context beyond these: it specifies the data source ('CDC / NCHS'), update frequency ('updates daily'), return format ('Katzilla envelope { data, quality, citation }'), and details about quality scoring and citation contents. This enriches the agent's understanding 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 states the purpose, dataset, and filters; the second details the return format, quality metrics, and citation. Every phrase adds value (e.g., source attribution, update frequency, output structure), with no redundant or vague language. It is front-loaded with core functionality.

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, read-only query), rich annotations (covering safety and idempotency), and the presence of an output schema (implied by 'Returns the Katzilla envelope'), the description is complete. It covers purpose, usage context, behavioral details (source, updates, return format), and output semantics, leaving no significant gaps for the agent to operate 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?

Schema description coverage is 100%, with all three parameters (limit, year, cause) well-documented in the schema. The description mentions filtering 'by year, cause, and state' (though 'state' is not a parameter in the schema, which is a minor discrepancy). It adds minimal semantic value beyond the schema, such as example causes ('e.g., Heart disease'), but the schema already provides similar context. Baseline 3 is appropriate given high schema coverage.

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 explicitly states the tool's purpose: 'Query CDC open data for leading causes of death in the United States by year, cause, and state.' It specifies the verb ('query'), resource ('CDC open data'), dataset ('NCHS Leading Causes of Death'), and scope ('United States'), clearly distinguishing it from sibling tools like health__cdc-data or health__who-gho which cover different health datasets.

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 provides clear context for when to use this tool: for querying leading causes of death data from the CDC's NCHS dataset. It mentions filtering capabilities ('by year, cause, and state') and the data source/update frequency. However, it does not explicitly state when not to use it or name specific alternatives among the many sibling health tools (e.g., health__cdc-data for other CDC datasets).

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