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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds that results include award amounts, institutions, titles, and abstract excerpts, which is useful context but largely redundant with the output schema. It does not disclose additional behavioral traits like pagination limits or disambiguation strategies, so it adds minimal value beyond the 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 three sentences with zero fluff. It front-loads the core purpose in the first sentence, then lists optional filters, then describes output and use cases. Every sentence earns its place and is efficiently structured.

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 moderate complexity (6 params, 1 required), a rich output schema, and strong annotations covering safety and idempotency, the description is complete. It covers what the tool does, what it returns, and typical use cases. Since output schema exists, it needn't detail return values. No critical information is missing for an agent to invoke it 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?

All 6 parameters have descriptions in the schema (100% coverage), so the baseline is 3. The tool description mentions optional narrowing by first name, fiscal year, or active status, which aligns with schema parameters but adds no extra semantics (e.g., format, constraints, or edge cases). It does not compensate for any gaps since there are none.

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 states a specific verb and resource: 'Find NIH-funded research projects by principal investigator (PI) last name.' It clearly differentiates from sibling tools (nihreporter.projects.by_org, .search, .publications.by_project) by focusing on the PI dimension. The return fields are listed, making the tool's function unambiguous.

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 provides clear user contexts: 'Useful for biosketches, grant history lookups, and conflict-of-interest checks.' It does not explicitly mention when to use alternatives like by_org or search, but the purpose is clear enough that an agent can infer intent. It lacks an explicit 'when not to use' or alternative routing, but it's adequate.

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