nih_projects_by_agency

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds that it returns project counts (not project details) and provides examples of agencies, but does not disclose any additional behavioral traits like the default top-25 agencies or pagination. Given the annotations, this is adequate but not rich.

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 concise sentences: the first states the core function, the second gives illustrative examples, and the third provides a use case. There is no fluff or repetition, and the key action is front-loaded.

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 description covers the purpose, output type, and use case. It does not mention that the agencies parameter is optional or that it defaults to the top 25, but that information is present in the schema description. For a simple read-only aggregate tool with two parameters and no output schema, this is nearly complete.

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% (fiscal_year and agencies both have descriptions). The description adds semantic context for agency codes (e.g., NCI for cancer, NIAID for infectious diseases) but does not explain how to use the parameters beyond what the schema already provides. This is a minimal addition above the baseline of 3.

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 verb 'Get', the resource 'project counts', and the scope 'by NIH institute/center for a fiscal year'. It also provides concrete examples of the output (NCI, NIAID) and ties it to a use case (understanding NIH budget allocation). This is specific enough to distinguish it from other NIH tools like nih_search_projects, which focus on individual projects rather than aggregate counts.

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 a use case ('useful for understanding NIH budget allocation across disease areas') but does not explicitly state when to use this tool over alternatives such as nih_search_projects or nih_spending_by_category. There is no mention of when not to use it or any exclusions, so the agent has to infer its role from the name and description.

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