nih_search_projects

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

The annotations already carry the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the description does not need to restate it. It does add the expected return columns, but it does not disclose pagination behavior, response limits, error/empty-result semantics, or any rate-limit note. The bar is lower given the annotations, but there is room for more operational context.

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 and each sentence is generally useful: purpose in sentence 1, returned fields in sentence 2, example use cases in sentence 3. The third sentence partially repeats the first one (e.g., 'disease area' vs 'any disease', 'institutional funding' vs 'investigator/funding'), introducing some mild redundancy, but the overall structure remains clean and compact.

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?

The 17 parameters are fully documented in the input schema, the output fields are defined in the description despite the lack of an output schema, and the annotations cover the safety/path profile. The description only lacks a minimal query example and a note about default pagination behavior, which can be inferred from the highly documented limit/offset parameters.

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% and each parameter already has both type, default/limits, and examples in the input schema. The description's mention of search facets merely re-aggregates what the schema already documents with more detail, so the Freeform text adds little semantic value beyond the schema.

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 begins with a specific verb and resource: 'Search NIH-funded research projects' and lists the key filter dimensions (text, disease area, PI, institution, state, agency, spending category, grant type, funding amount). It also enumerates the return fields, which immediately distinguishes it from sibling tools like nih_search_publications and nih_spending_by_category.

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 provides concrete use cases in the final sentence: 'find research grants for any disease, track institutional funding, or identify PIs.' However, it does not explicitly name alternative tools or define when an agent should choose a sibling search, so it stops short of full exclusion guidance.

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