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

Beyond annotations (readOnly, idempotent, non-destructive, openWorld), the description discloses provenance (Form 13 reports, filing ids/dates, coverage dates), privacy handling (withheld organisations shown only as counts/amounts, individuals never named), analytical constraints (never added across years, never put in sequence), and the mandatory question note and FEC 52 U.S.C. 30111(a)(4) restriction. This is exactly the kind of behavioral context annotations cannot convey.

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 core statement is front-loaded in the first clause, but the bulk is a single enormous comma-spliced run-on enumerating every returned component, followed by a paragraph of caveats that restates the same non-additivity and privacy points ('never added across years' / 'never added or put in sequence'). Much of the legal boilerplate could be compressed without losing meaning.

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?

With no output schema, the description carries the full burden of explaining what comes back, and it does so comprehensively: cumulative totals with accepted/refunded/net kept apart, filing ids and dates, organisation vs individual breakdowns, withheld categories, cross-year family comparisons, LD-203 cross-check counts, coverage counts, and headlines. An agent knows the scope, limitations, and nature of the response before calling.

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 tool takes no parameters, so there is nothing for the description to disambiguate; baseline for a zero-param tool is 4. The description cannot and need not add parameter meaning.

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 names the specific resource (Inaugural Donors Register, built from Form 13 filings by the 2025 and 2021 committees) and the operation (returning totals/aggregates). It implicitly distinguishes itself from the donor-level sibling by stressing 'Individual donors are counted, never named,' but never names inaugural_donors_donor directly, so sibling differentiation is inferential rather than explicit.

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?

Usage is only implied: the register nature and the 'counted, never named' privacy rule signal this is the aggregate view rather than the per-donor lookup. There is no explicit 'use this when…' or 'use inaugural_donors_donor instead for named donors,' and no prerequisites or exclusions are stated.

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