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

Annotations already indicate read-only, idempotent, non-destructive behavior, so the description is not required to repeat those. It adds valuable context: 'No auth — US Gov public domain' and the source dataset ID (hksd-2xuw), which informs the agent about access and provenance. This is beyond annotation coverage and enhances transparency.

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 four sentences, each with a distinct purpose: state function, define return values with examples, mention optional filtering, and provide scope/source/auth. It is front-loaded with the primary action and contains no filler or repetition. This is an exemplar of efficient, well-ordered documentation.

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 listing tool with a single optional filter, the description covers the essential information: what is returned, how to filter, scale of data, source, and access. It does not mention pagination, but given the small dataset (19 topics, 100+ questions) and the presence of an output schema, this is likely not a critical gap. The inclusion of the dataset ID and public-domain note makes it complete enough for an agent to invoke correctly.

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 single parameter `topic_id` is fully documented in the schema with a complete enum and per-value descriptions (100% coverage), so the description's mention of 'Optionally filter to a single topic' is redundant. The description does not add syntax or format details beyond what the schema provides. Baseline of 3 is appropriate because the schema carries the explanatory burden.

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 function: 'List all available chronic disease topics and their associated indicator questions in the CDC CDI dataset.' It specifies the returns (topic IDs and question IDs) and even gives concrete examples (DIA=Diabetes, CVD01=High blood pressure). The parenthetical mention of other cdc_chronic tools distinguishes it as a reference/lookup tool, setting it apart from sibling tools like state_compare or trend.

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 use as a prerequisite for other cdc_chronic tools ('needed for other cdc_chronic tools'), establishing when to invoke it. It notes the optional filter and mentions the full scope (19 topics, 100+ questions). While it doesn't explicitly exclude other tools, the framing as a discovery/listing tool is clear. Given the tool's self-contained nature, this is adequate guidance.

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