NCHS leading causes of death by state (bi63-dtpu). Returns total deaths and age-adjusted death rates per cause per state per year. Useful for chronic disease + injury mortality research.
| Name | Required | Description | Default |
|---|---|---|---|
| year | No | Year | |
| limit | No | Max rows (default 50) | |
| state | No | Full state name or 'United States' | |
| cause_name | No | Cause name (e.g. 'Heart disease', 'Cancer', 'Suicide') |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds the output composition and grain (deaths and age-adjusted rates by cause/state/year) but does not disclose behaviors such as no-parameter aggregation or pagination. With strong annotations, the added value is acceptable 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?
Three short sentences, each earning its place: source/dataset ID, precise return contents, and the intended research use. It is front-loaded and contains no filler.
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 four-parameter read-only aggregation tool with no output schema, the description's statement of returned measures and dimensions is largely sufficient. It does not describe what happens when no filters are supplied, but the schema's fully documented optional parameters and the broad openWorld hint mitigate that gap.
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%, and each parameter already has a useful description such as 'Full state name or United States' and 'Cause name (e.g. Heart disease...)'. This meets the baseline; the tool description adds no extra parameter-level semantics.
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 names the resource ('NCHS leading causes of death by state') and the exact output ('total deaths and age-adjusted death rates per cause per state per year'). It does not explicitly compare against sibling CDC tools, so it stops short of a full 5, but the dataset ID (bi63-dtpu) helps identify it uniquely.
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?
'Useful for chronic disease + injury mortality research' gives a clear research context for when to call this tool. It does not name any alternative CDC mortality tool or state when not to use it, so it lacks explicit exclusions.
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.