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

Beyond the annotations (readOnly, openWorld, idempotent), the description discloses important behavioral traits: results disclose truncation, and figures represent reported federal obligations—not valuation, revenue, or total research spending. This prevents misinterpretation of the data and adds context that annotations alone do not provide.

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 two sentences, front-loaded with the main action and purpose. It avoids filler and every clause adds value (scope, output dimensions, truncation disclosure, data semantics).

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?

Given the tool's complexity (5 optional parameters, no output schema), the description covers the search scope, output granularity, and data interpretation. It does not explain pagination, limit defaults, or how parameters combine (e.g., AND vs OR), but the examples in the schema partially fill this gap. The description is adequate for a read-only, bounded aggregation tool.

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 description mentions 'topic, organization, or PI search' which maps to the query, organization, and pi_name parameters, adding some meaning beyond the bare schema. However, it does not explain the fiscal year parameters (to_fiscal_year, from_fiscal_year) or their expected format/behavior. Since schema coverage is 0%, the description only partially compensates for missing parameter documentation.

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 uses a specific verb ('Summarize') with a clear resource ('NIH award dollars and record counts') and defines the grouping dimensions (fiscal year, recipient organization, PI, activity code, funding mechanism). It distinguishes this tool from siblings like nih_funding_expirations or nih_grant_award_history by focusing on concentration/summary rather than individual awards or expirations.

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 phrase 'bounded topic, organization, or PI search' provides clear context on when to use the tool, implying the user should narrow their query to one of these scopes. However, it does not explicitly mention alternatives or when not to use it, so a small deduction from 5 is applied.

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