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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable context beyond annotations: it names data sources, lists the tables and their contents, and discloses that free keys only return race totals and national/regional/state donor geography, with deeper tables requiring a paid PoliSpend subscription. It does not mention rate limits or return pagination, but the paywall detail is a meaningful behavioral disclosure.

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?

The description is front-loaded with the core purpose and then densely lists table contents, all of which earn their place by clarifying the required 'table' parameter. The run-on sentence structure and semicolon-heavy list are less scannable than a bulleted format, but there is little wasted text.

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?

Given four parameters, no output schema, and a complex multi-table dataset, the description does a good job explaining what each table contains and the cycle/free-tier limits. It omits explicit return formatting (e.g., rows vs. aggregated JSON) and filter interaction details, but the table descriptions give an agent enough to call it 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 coverage is 50%, with descriptions for cycle and state but none for table and office. The description compensates substantially by explaining each table enum value (e.g., 'races (per House/Senate race: candidate receipts, outside spending for/against)' and 'donor_geo (donations by city/state/division/region)') and by naming cycle values (2026 plus 2022 and 2018). Office is only indirectly covered via 'House/Senate race', so a small gap remains.

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?

The description clearly identifies the resource as US election money data from FEC and state/city filings, and enumerates the tables available (races, candidates, donor_geo, etc.). It does not differentiate from siblings, but no sibling covers political spending, so the purpose is unambiguous.

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?

The description implies usage by listing the dataset's contents and cycles (2026, 2022, 2018), but it never states when an agent should call this tool versus another, nor does it give explicit exclusions or prerequisites. The free-vs-paid tier note adds context but is not framed as usage guidance.

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