nih_spending_by_category

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the description only needs to add behavioral context. It adds the RCDC-category mechanism, an agency-based fallback, and the output (project counts and estimated funding), matching the read-only safety profile and adding useful details beyond annotations.

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 compact and front-loaded, with no filler. The core purpose comes first, the mechanism and accuracy caveat follows, and the helpful category-ID list and sibling routing are placed at the end. Every sentence earns its place.

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 small parameter count, full schema coverage, and strong annotations, the description covers the essential usage context: what the tool returns, how category selection works, and a relevant alternative. The lack of an output schema is acceptable because the description names the return content, so an agent has enough to call the tool correctly.

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 description coverage is 100%, so the schema already documents both parameters and even repeats the first five category IDs. The description adds a few additional common category IDs beyond the schema and frames the purpose of category_id, but it does not materially deepen parameter meaning beyond the schema. Baseline 3 is appropriate.

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: 'Get NIH project counts and estimated funding for a disease/research area across fiscal years.' It also clarifies the mechanism (RCDC spending categories) and distinguishes the tool from the sibling nih_projects_by_agency by pointing to that alternative for more reliable counts by disease area.

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 gives practical selection guidance: this tool provides category-based counts and funding across fiscal years, with a fallback approach for accuracy. It explicitly suggests nih_projects_by_agency when the most reliable counts by disease area are needed. However, it does not explicitly state when not to use this tool or enumerate other alternatives.

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