Look up Census FIPS codes by name. Supports state name or 2-letter code, ZIP code (5 digits), and (for state) substring matching. Use this to find the FIPS codes needed by other census_* tools.
| Name | Required | Description | Default |
|---|---|---|---|
| level | No | Optional filter: state, county, zcta, place. | |
| limit | No | Max matches (default 10). | |
| query | Yes | Free-text: state name ('Texas'), state code ('TX'), or 5-digit ZIP ('77301'). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, so the safety profile is covered. The description adds meaningful behavioral detail beyond annotations: accepted input formats, ZIP code digit requirement, and substring matching for states. It does not discuss response shape or limit behavior, but those are secondary for a read-only lookup.
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 compact sentences lead with the core action, then add supported query formats, and close with the cross-tool use case. Every sentence earns its place and there is no redundant restating of the tool name or schema.
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 read-only helper with complete parameter schemas and strong annotations, the description covers purpose, query formats, and why an agent would choose it. The main gap is the absence of any response-shape description, which matters more because there is no output schema, but the core lookup guidance is sufficient for correct invocation.
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%, so the schema already documents all three parameters. The description adds value by specifying exactly what free-text query accepts (state name, state code, 5-digit ZIP) and that state matching can be partial, which goes beyond the schema's generic 'Free-text' description.
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 action ('Look up') and resource ('Census FIPS codes'), and immediately clarifies the supported query forms: state name/code, ZIP, and state substring matching. It also distinguishes this tool from the many other census_* data tools by framing it as the FIPS-helper those tools depend on.
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 explicitly tells the agent when to use this tool: to find the FIPS codes required by other census_* tools. It does not explicitly state when not to use it or name an alternative lookup tool, but the dependency relationship with the census family is clear and actionable.
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.
Many tools overlap heavily across domains: caselaw_search vs court_case_search vs court_opinion_search, caselaw_citation_lookup vs court_citation_resolver, and a cluster of company due-diligence tools (company_trust_check, counterparty_risk_score, entity_dossier, issuer_diligence_dossier, kyb_aml_evidence_case_file) that all screen a company for sanctions/risk/standing. With 290 tools, an agent will frequently face multiple equally plausible choices for the same user intent.
The vast majority of tools follow a clean domain-prefix + snake_case pattern (census_, eia_, fmcsa_, npi_, cfpb_, etc.), but there are notable exceptions: entity_resolve and resolve_entity are reversed duplicates, reg_search (Federal Register) sits next to reg_cfr_search (CFR) with confusingly similar names, and carrier_monitor_recheck deviates from the carrier_vetting_* family.
290 tools is an extreme count under any rubric, far exceeding even the 50+ threshold for the lowest score. While the group-filtering mechanism and meta-tools like list_tool_groups and search_available_datasets mitigate the practical burden, the raw surface is still massively oversized for an agent to select from accurately and efficiently.
For a read-only data-aggregation server, coverage is remarkably comprehensive across 59 domains, and generic fallbacks like cdc_dataset_query, eia_series_lookup, fred_observations, and bls_series prevent most dead ends. Minor gaps exist (a single GitHub tool, demo-only property_lookup coverage, no write/update operations anywhere), but the stated data-access purpose is well served.