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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, establishing a safe read-only operation. The description adds valuable behavioral details: a limit of 25 results per call, sorting by award amount descending, and the inclusion of a URL to the full project. These enrich the agent's understanding beyond the annotations, although it does not mention pagination behavior (offset parameter) explicitly.

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, front-loaded with the core purpose, followed by return details and filtering options. There is no redundancy or extraneous information. Every sentence contributes useful context, making it highly concise and well-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 output schema exists, the description does not need to detail the exact return structure, but it still lists the key fields in prose, which helps the agent anticipate the content. It covers the limit, sorting, and filter options. It does not mention pagination via offset, but that is available in the schema. Overall, it is sufficiently complete for an agent to call the tool correctly, though it could be more explicit about pagination.

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 all parameters are documented. The description adds extra context by providing examples for agency (NCI, NIDDK, NIAID, NIMH) and clarifying the keyword parameter can be a disease, drug, or technique. This goes beyond the schema descriptions, which list generic examples, giving the agent more concrete guidance on parameter values.

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 clearly states the tool's function: 'Search NIH-funded research projects by keyword, disease, drug, or technique.' It also enumerates the return fields (PI names, institution, award amount, etc.) and mentions filtering options, distinguishing it from sibling tools like nihreporter.projects.by_org and by_pi, which search by different criteria. The verb 'Search' and resource 'NIH-funded research projects' are explicit, making the purpose 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 implies usage for keyword-based searches ('Search by keyword, disease, drug, or technique') but does not explicitly name alternatives or state when not to use this tool. While the sibling tools (by_org, by_pi) are clearly different, the description does not guide the agent to choose this tool over them, leaving the selection to inference rather than explicit guidance.

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