find_agencyResolve a federal agency name fragment to its official awarding-agency names (toptier and subtier) as USAspending knows them - use before search_awards or spending_by_category when unsure of the exact agency name. Keyless.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Agency name fragment, e.g. "navy" or "DISA" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover readOnly, openWorld, idempotent, and destructive safety hints. The description adds 'Keyless' (no authentication required) and clarifies the output mapping to toptier/subtier names, which are meaningful beyond the structured annotations. No contradiction exists.
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 with no fluff. The first sentence states the core purpose and output, the second provides usage guidance and 'Keyless' note. Information is front-loaded and every word earns its place.
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?
For a simple one-parameter lookup tool with strong annotations, the description is complete: it explains the operation, expected output (toptier/subtier names), and usage context. No output schema is present, but the return value is conceptually described. The guidance also covers when not to use it.
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%, with the parameter described as 'Agency name fragment' and examples 'navy' or 'DISA'. The description does not add extra parameter semantics beyond the schema, so the baseline score of 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?
The description uses the specific verb 'resolve' and clearly identifies the resource as 'federal agency name fragment' with the output being 'official awarding-agency names (toptier and subtier)'. It also distinguishes itself from sibling tools by referencing search_awards and spending_by_category, making its 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?
Explicitly states 'use before search_awards or spending_by_category when unsure of the exact agency name', providing clear when-to-use context and naming alternative tools. This fully addresses usage guidance.
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 clearly distinct purpose: two are code/name resolvers, two are searchers (awards vs opportunities), one fetches award details, one looks up entities, and one aggregates spending. No two tools overlap in function, and descriptions reinforce the boundaries.
All tool names follow a consistent snake_case verb_noun pattern (find_agency, find_naics, get_award, lookup_entity, search_awards, search_opportunities, spending_by_category). The use of 'lookup' instead of 'find' is a minor stylistic variation but does not break the overall pattern.
Seven tools is well-scoped for a federal market intelligence server, covering the essential operations of entity resolution, searching, detail retrieval, and aggregation without unnecessary bloat. Each tool earns its place.
The tool set provides strong coverage of the federal market research workflow: resolving agencies and NAICS codes, searching opportunities and awards, retrieving award details, vetting entities, and aggregating spending. The only notable gap is the absence of a dedicated 'get_opportunity' tool to mirror 'get_award' for retrieving full opportunity details.