search_nih_grantsSearch NIH-funded research grants by state, institution, or topic. Returns project title, principal investigator, award amount, NIH institute, and organization.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results (default 25) | |
| state | No | Two-letter state code (e.g., MD) | |
| topic | No | Research topic or keyword | |
| institution | No | Research institution name |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and openWorldHint. The description adds no extra behavioral traits beyond what is in annotations (e.g., no mention of pagination, data freshness, or other quirks). No contradiction with 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?
Two sentences: first states purpose and filters, second lists returned fields. Extremely concise with no filler, front-loading key information efficiently.
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?
Tool has 4 optional parameters and no output schema. Description covers purpose, input filters, and output fields adequately. However, it omits details like sorting, default limit behavior (though schema mentions default 25), or any restrictions—minor gaps for a complete picture.
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 coverage is 100% and descriptions are already informative (e.g., state as two-letter code, limit with min/max). The description only lists parameter names without adding deeper semantic meaning or usage tips, so 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?
Description clearly states the tool searches NIH-funded research grants, specifying parameters (state, institution, topic) and return fields (project title, PI, award amount, etc.). This distinguishes it from sibling search tools like search_colleges or search_consumer_complaints.
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?
Description implies usage for searching grants by defined filters but does not provide explicit guidance on when to use this tool versus alternatives, or when not to use it. There are no exclusions or context for selecting this tool among many search tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clear, specific purpose with detailed descriptions that differentiate them. Prefix patterns like get_district_, search_, analyze_, get_, etc., help an agent easily identify the correct tool for a task.
All tool names use a consistent verb_noun or verb_noun_noun pattern with underscores. The naming convention is uniform across the entire set, with no mixing of styles or ambiguous verbs.
With 47 tools, the count is high but justified by the broad scope of civic data analysis. While some agents might find the sheer number overwhelming, the tools are organized into clear categories (district profiles, searches, analyses) that make navigation feasible.
The toolset covers an impressively wide range of domains: legislation, representatives, districts, voting, committees, campaign finance, lobbying, federal spending, regulations, environment, energy, healthcare, housing, disaster, banking, consumer complaints, crime, vehicles, and more. There are no obvious missing operations for a civic data platform.