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

Annotations already declare read-only, non-destructive, closed-world; the description adds substantive behavior beyond them: data source (T-MSIS), period, percentile methodology, the exact fallback semantics ('no_source_at_this_level' with next level up), source URL per figure, the children_only/not_verified age-scope caveat, and a privacy statement. It also preempts a likely misreading by stating these are paid amounts, not patient charges.

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?

Front-loaded with the trigger and the return shape before caveats and exclusions, so the critical information comes first. It is dense and carries some redundancy (the 'not what a patient is charged' point is restated by the 'not a quote' disclaimer), but nearly every clause adds routing or interpretation 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?

No output schema exists, and the description compensates by describing the return payload in detail: per-claim-line amount, percentiles, state cell with rank and official fee, national cash band, per-figure source URL and period, and the missing-data status. Combined with the privacy and advice disclaimers, nothing material is left unspecified.

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 the baseline is 3; the description goes further by explaining what supplying `state` actually changes (adds the state cell with rank and official fee, subject to age scope) and by demonstrating Spanish output via `lang` in the example phrasings. It does not explain syntax beyond the schema's pattern, which keeps it below a 5.

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 and resource (what Medicaid pays/payed per claim line for a CDT code), plus scope: national vs. US state, T-MSIS 2018-2024 percentiles. It is clearly separable from siblings like medicaid_adult_dental_rules (eligibility rules) or dental_cost_by_state (charge-based costs).

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?

Opens with an explicit 'Use this when...' trigger, supplies four representative phrasings in English and Spanish, and adds an explicit 'Do not use for' exclusion list (diagnosis, treatment choice, named insurer plan price, non-US/Canada). This is about as complete as routing guidance gets.

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