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

Annotations already cover safety (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint), so the bar is lower. The description still adds non-redundant context: data provenance and freshness ("Data is live from ProPublica Nonprofit Explorer") and a scope limitation beyond the annotations ("Does not rate or rank organizations"), which heads off a natural misinterpretation of a tool named 'compare'. It does not mention cost, rate limits, or failure modes for invalid EINs, keeping it short of a 5.

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?

Four sentences, front-loaded with the usage trigger and with the alternative-tool steering placed last, which reads naturally. The output enumeration is dense but each item is concrete rather than filler. Minor length cost from listing the exact return fields even though an output schema exists.

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 single-parameter, read-only tool with full schema coverage, rich annotations, and a declared output schema, the description covers trigger, inputs, provenance, and scope limits. The only real gap is the unresolved 2-to-5 versus maxItems-50 discrepancy in the accepted EIN count, which the description does not reconcile.

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 baseline is 3; the description earns above that by adding EIN format guidance implicitly through the EIN-keyed workflow and by tying the parameter to the search_nonprofits prerequisite for name-based requests. It is docked because it asserts a 2-to-5 EIN range while the schema permits maxItems 50, leaving an agent unsure which bound is authoritative.

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 a specific verb and resource ("compare 2 to 5 US nonprofits side by side by EIN") and enumerates the concrete outputs returned (Form 990 revenue, expenses, net assets, assets, officer comp, computed ratios with formulas, PDF/CSV/Excel exports). It also states what it is not ("Does not rate or rank organizations"), so an agent can distinguish it from get_nonprofit_profile and search_nonprofits without opening any 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?

It gives an explicit trigger ("Use this when the user wants 2 to 5 US nonprofits side by side by EIN"), an explicit exclusion ("Do not use with names"), and a named prerequisite/alternative ("find EINs with search_nonprofits first"). This is the full when/when-not/alternative triad with a routing dependency to a sibling tool.

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