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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds material behavioral detail beyond that: max 25 results, the presence of revenue/assets/health scores with a 0–100 scale, acceptance of raw NTEE letters, the underlying ProPublica API, a 30/minute rate limit, and no-auth requirement. This fully discloses what the agent needs to know about side effects and constraints, with no contradiction.

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 follows with essential details, then routing instructions. While it is longer than average, every sentence contributes: category mapping, rate limit, no-auth, and feedback fallback. No redundant fluff, though the feedback instruction could be condensed slightly. Overall it is well-organized and earns its length.

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 2-parameter tool with a clear output schema (implied by the mention of revenue/assets/health scores) and read-only annotations, the description covers everything an agent needs: input constraints, response size, expected fields, rate limits, authentication status, and follow-up paths. Nothing critical is missing for correct invocation.

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% (both params have descriptions), so baseline is 3. The description enriches the category parameter by enumerating all NTEE categories and noting that raw letters (A–Z) are also accepted, which is not in the schema. The state parameter is adequately defined in both schema and description. This adds value beyond the schema without fully compensating for the lack of enums (though enums are not present).

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, and scope: 'Search US nonprofits by mission category and state.' It also lists the category choices and clarifies the return fields, making the tool's function unambiguous and distinct from sibling nonprofit_search_nonprofits_by_name, which searches by name instead.

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 explicitly positions this as a 'Starting point for nonprofit due diligence' and directs the agent to nonprofit_fetch_nonprofit_full_profile for deeper investigation. It also includes a conditional fallback to report_feedback with a detailed template, telling the agent when and how to escalate. This is explicit when-to-use and alternative guidance.

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