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

Annotations declare readOnlyHint=true and idempotentHint=true, so the safety profile is already covered. The description adds valuable context beyond that: the data freshness caveat ('lags 1–2 years'), the source attribution ('ProPublica Nonprofit Explorer, sourced from IRS Form 990 filings'), and the note that the tax year is displayed prominently to avoid misreading stale data. This behavior — returning potentially dated financials that require interpretation — is exactly the kind of nuance 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 description is dense but every sentence earns its place: the first sentence inventories the return payload, the second covers the standing/classification fields, the third routes to the sibling, and the fourth handles data lag and provenance. The most decision-relevant line ('use nonprofit_search first... requires an EIN') is placed third but the leading payload inventory is front-loaded appropriately. No filler or redundancy.

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?

Complete for a single-parameter read tool. An output schema exists, so return-value documentation is handled structurally. The description covers the data source, freshness caveat, sibling routing, and required parameter format. The only thing an agent might want — average field-level detail for every return value — is available in the output schema. Nothing needed for correct invocation or result interpretation is missing.

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 the schema fully documents the ein format (integer with leading-zero caveat, or string with optional hyphen). The description adds meaning beyond the schema by specifying where the EIN comes from ('Obtain from nonprofit_search results'), which tells the agent the provenance of the parameter and reinforces the tool-routing decision. It also explains what the parameter is used for (keying into the full profile), which the raw schema's 'Employer Identification Number' label does not.

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 ('returns a full profile') and resource ('single tax-exempt org by EIN'), enumerating the exact fields delivered (legal name, address, NTEE, 501(c) type, ruling date, financials, BMF standing). This cleanly distinguishes it from siblings: it is the rich single-record getter, while nonprofit_get_filings covers filings and nonprofit_search is the discovery tool. No ambiguity survives.

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?

Explicitly tells the agent when to use this tool vs. the sibling: 'Use nonprofit_search first if you only have an org name — this tool requires an EIN.' It also sets expectations about data recency ('Data lags 1–2 years'), which is a usage constraint the agent needs to decide whether the tool fits the user's needs. Both conditions for correct use are stated directly.

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