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

Annotations already cover read-only/idempotent/non-destructive, and the description still adds substantial value beyond them: it names the two returned collections, discloses the heterogeneous Mississippi state-authority source with unmatched candidates, discloses ordering ('by reported receipts, not an endorsement'), and warns that neither collection proves ballot certification or complete coverage. That is exactly the kind of caveat an agent cannot get from structured fields.

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 purpose and query surface, then caveats — good ordering with no filler paragraphs. A few clauses ('No party is excluded', 'not an endorsement') read as legal boilerplate and could be compressed, but each still carries an anti-bias signal an agent might otherwise over-interpret.

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 5-param, zero-required search with an output schema, this is close to complete: it explains both result collections, coverage limits, and a hand-off rule. It stops short on how results are truncated/paged when `limit` caps at 20 and on office code semantics, which an agent may need to call correctly.

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 20% (only 'state' is documented), so the description must carry the load and it covers roughly half: it maps q to 'public name or FEC ID' and lists state/office/district as filters. It never explains the H/S/P office codes, the two-digit district format, or what `limit` (default 5, max 20) controls, leaving real gaps.

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?

Opens with a specific verb+resource+scope: 'Search Election.org's 2026 FEC candidate filings by public name or FEC ID, state, office, or district.' It implicitly separates itself from get_campaign_finance via 'Do not request federal finance for a null FEC ID,' but never names that sibling or search_offices explicitly, so discrimination is good rather than airtight.

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 concrete operational direction: 'Check both collections' (data.records and data.state_authority_records), and the negative rule 'Do not request federal finance for a null FEC ID' tells the agent when to stop and hand off to finance tooling. Missing an explicit statement of when to prefer search_offices or get_election_results instead, so not a full 5.

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