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

Annotations already declare readOnly, idempotent, non-destructive, openWorld, so the safety profile is covered. The description still adds real behavior: the enumerated supported years, the hard-fail (not fallback) semantics for unsupported years, and the presence of calculation caveats and record links. No auth or rate-limit context, but the error contract is the important disclosure here.

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?

Five short sentences, front-loaded with the verb and resource, then scope, then the supported-year constraint, then the negative boundaries. No filler and no repetition of annotation data.

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?

Return values need not be explained since an output schema exists, and the year contract is fully covered. The gap is the four undocumented optional filters (limit, office, district, candidate): an agent cannot tell from the definition how to narrow a query to a specific race without reverse-engineering the 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 description coverage is 17% — only `state` is documented. The description meaningfully narrows `year` from the schema's 1900–2100 range down to five supported values, which is a genuine semantic addition. However, `limit`, `office`, `district`, and `candidate` receive no explanation in either schema or description, leaving most of the filtering surface opaque.

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 (Retrieve) and resource (U.S. House and Senate election results) with a precise scope qualifier ('explicitly requested year'). It also carves itself away from adjacent tools by naming what it is not: live returns, projections, presidential results — which separates it from get_election_calendar and get_campaign_finance.

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?

Clear when-not guidance: other years produce an unsupported-year error and never substituted historical results, and the tool explicitly excludes live returns, projections, and presidential results. It stops short of naming a sibling as the alternative for presidential or live-race queries, so it is strong context without full routing.

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