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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), yet the description adds substantive behavior: values are survey ESTIMATES with margins of error, suppressed estimates return null rather than being imputed, provenance lives in dataset_version/period, and every response carries a sources[] array with licence. It also discloses billing at 1c.

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 output in the first sentence, then composition, caveats, usage, billing, and provenance in scannable chunks — every section does work. Slightly padded by the internal spec reference (§22.2) and the standalone billing/sources lines, which cost a little tightness.

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 shape need not be spelled out, and the description still volunteers the estimate/null semantics and provenance fields an agent would otherwise misread. Given the composition of two datasets and the zero-required-parameter signature, nothing needed for correct invocation is missing.

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 only 33% (lat/lon carry no descriptions), so the description must carry weight. It clarifies that lat/lon form a point coordinate and that geoid is a 5-digit county key that bypasses the boundary lookup, which is real value. It stops short of stating pairwise/single-input requirements or the lat/lon unit conventions.

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: population and median household income for the county containing a point, from ACS 5-year estimates. It also names the pipeline (TIGER/Line GEOID resolution then ACS read), which separates it from census_geocode and admin_areas without opening a 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?

An explicit 'When to use' line gives the user-intent phrasing ("how many people live in this area") and routes the agent: supply a coordinate, or reuse a county GEOID from the sibling tool admin_areas. The geoid-passthrough condition is stated with its consequence (skips the boundary lookup).

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