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

Annotations already declare it as a read-only, closed-world, non-destructive lookup, and the description adds real substance on top: survey-weighted figures, data vintage (2023-2024), 95% confidence intervals on the change, a source URL and period on every figure, and the caveat that results are not a quote or medical advice. With no output schema, it also enumerates what comes back (per-person spending, mean/median out-of-pocket, total spending, visit share).

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 condition and scope, then returns, then disambiguation, which is the right order. It is somewhat long: four verbatim example queries and a trailing compliance sentence ('Market research and public program data... not a quote, not medical advice') add bulk beyond what an agent strictly needs.

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 zero-required-parameter informational lookup, the definition covers everything an agent needs: what is returned, the data source and vintage, the statistical treatment (survey weighting, confidence intervals), the geographic and topical boundaries, and the sibling to use instead for procedure-level costs. Nothing material is left ambiguous.

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 `lang` parameter is fully documented in the schema, so the description doesn't need to restate it. It does add value by including example Spanish queries ('¿cuánto gasta al año un estadounidense en el dentista?'), which signals that the Spanish response mode is a real supported path rather than a technicality.

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+scope: national US dental spending, out-of-pocket share, and visit prevalence from MEPS for 2023-2024. It explicitly distances itself from dental_cost_by_state ('procedure costs go to dental_cost_by_state') and from person-level vs procedure-level data, so an agent can separate it from siblings without opening the schema.

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 an explicit when-to-use clause, four concrete example phrasings (including Spanish), and a 'Do not use for' list covering diagnosis, insurer plan prices, non-US countries and dentist recommendations. It also names the correct alternative for procedure costs.

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