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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds valuable context beyond this: it clarifies the data is from CMS PUF, covers only HealthCare.gov states, and explains that the market filter selects issuers rather than splitting counts. It also explains the 'dental denies at much higher rates' nuance, which helps agents interpret results. It doesn't mention pagination or response format, but with openWorldHint true, missing data is expected.

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 dense but well-organized. It starts with the core purpose, then addresses common user questions, describes the return fields, explains the filters with caveats, and ends with data source and limitations. While it's a bit long, it avoids redundancy and front-loads the key information (what it does, what it returns). The structure is logical and information-dense, with each sentence adding value.

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 (4 optional params, no output schema), the description is quite comprehensive. It covers purpose, data source, filter semantics, data coverage limitations, and return fields (claims received, denied, denial rate, plans offered). It doesn't discuss error conditions or edge cases (e.g., no matching issuers), but with no required params and no output schema, the main contextual needs are addressed. A small gap is not mentioning sorting behavior aside from order param, but that's in schema.

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 coverage is 100%, so parameters like state, market, limit, and order are already documented. The description adds critical context: it explains the market parameter's semantics in depth (it selects issuers, not claims counts, and gives examples like 'Individual QHP' and 'Individual SADP'), which goes beyond the schema's basic definition. It also explains that 'state' is two-letter code, though that's in the schema. This added value justifies above baseline 3.

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: ranking health insurers by claim denial rates. It specifies the data source (CMS TiC PUF), the plan year (2026), and the exact questions it answers. It also distinguishes itself from sibling tools like insurer_appeal_outcomes, insurer_denial_coverage, and insurer_denial_profile by its focus on denial rates and issuer-level ranking, making selection unambiguous.

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 explicit guidance on when to use this tool: for questions about denial percentages, comparisons between insurers, and state-level breakdowns. It also notes important exclusions (state-run exchanges like CA and NY are not covered) and explains the market filter's behavior (selects issuers, not claims splits), which helps agents decide if this is the right tool or if a sibling like insurer_denial_profile might be more appropriate.

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