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

Annotations already declare readOnly/openWorld, but the description adds genuinely non-structured behavior: a $0.002 USDC charge per successful call via x402, with failed calls not charged, and a 50-row ceiling. That payment model materially affects invocation decisions. It stops short of noting data recency or which years are actually populated.

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?

Four compact sentences, front-loaded with what the data is, then the caveat, the limit, and the price. No filler; every clause carries information an agent would act on.

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?

An output schema exists, so return values need no explanation, and the cost/row-limit guardrails are covered. Minor gap: no indication of available year range or what happens when the state name doesn't match the dataset spelling, which matters for a single required parameter.

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%, so each of max/year/state is already documented with types, defaults and examples. The description only echoes "by US state and year" and adds the rate unit, providing no syntax or format detail beyond the schema. Baseline 3 applies.

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?

States a specific verb+resource: "CDC/NCHS leading causes of death by US state and year", plus the exact metrics returned (cause, deaths, age-adjusted death rate per 100,000). It also distinguishes itself from the CDC WONDER query tool, so the agent knows this is the published table, not the queryable database.

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?

Gives clear context (data.cdc.gov open data, published table, not the WONDER query tool) and a hard operational limit of 50 rows per call. It does not, however, route the agent among the many sibling health datasets (e.g. fluview or WHO stats) that could plausibly be confused with mortality data.

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