Nonprofit Leads: IRS Charities & Foundations by State

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

Annotations already declare read-only, open-world, non-destructive, non-idempotent, but the description adds real substance beyond them: per-result pricing ($0.001), a hard per-call spend cap via run_max_charge_usd, free runs on zero matches, the interaction where run_max_items fills maxResults when unset and can therefore under-bill relative to maxResults, expected latency (5-15 s typical, minutes for large inputs) and the 300 s timeout remedy. It also flags data-quality caveats (in-care-of/address may be a PO box or attorney) that an agent would otherwise misread.

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, then differentiators, then usage, then parameters, then runtime/pricing behavior — a logical hierarchy that lets an agent stop reading early. It is long and has minor redundancy (the free-on-no-match point is stated twice, and maxResults-as-cost-cap is repeated), which keeps it off a 5.

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 17-parameter, zero-required, no-output-schema tool, the description supplies the return field list, response envelope ({actor, count, items} plus structuredContent and NONPROFITS_XLSX/CSV), cost model, and timeout behavior. An agent has everything needed to call it correctly and interpret the result without an output 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 coverage is 100%, so 3 is the floor, and the description earns above that by adding decision guidance the schema lacks: states as 'the usual starting filter', sortBy/minAssets/minRevenue as the way to rank large prospects first, maxResults as the cost cap, and the run_max_items vs maxResults billing interaction. It also explains the field provenance for inCareOf and enumerates returned items.

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: builds nonprofit/foundation lead lists from the IRS Exempt Organizations Business Master File, with the filter surface enumerated. It explicitly contrasts itself with sibling tools (local_business_leads for OSM shops, npi_provider_lists for healthcare NPIs), so an agent can disambiguate 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?

Gives positive triggers (fundraising, sponsorship, grants outreach, nonprofit CRM enrichment) and explicit exclusions with named alternatives (for-profit businesses -> local_business_leads or company_website_enricher; Form 990 full-text analysis -> not this tool). This is the when/when-not/alternative pattern at full strength.

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