CDC excess deaths associated with COVID-19 (xkkf-xrst). Modeled expected vs observed deaths by state and week. Used to estimate true pandemic impact beyond reported COVID deaths.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max rows (default 50) | |
| state | No | Full state name (e.g. 'Texas') or 'United States' | |
| outcome | No | Outcome (e.g. 'All causes', 'All causes, excluding COVID-19') |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful context about the data model (modeled expected vs observed, by state and week) beyond the annotations, but it doesn't disclose response structure, pagination, or other behavioral traits.
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 compact sentences, each earning its place: dataset identifier, data content/dimensions, and intended use case. The identifier is front-loaded, and there is no redundant filler or repetition of the title.
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 read-only dataset lookup with complete schema documentation and no output schema, the description covers the core need: what data is included, how it is organized, and why an agent would use it. The absence of an explicit verb and minor lack of detail on filtering behavior are small gaps, but the definition is largely 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%, so the schema already documents all three parameters: limit, state, and outcome. The description mentions 'by state and week' but no week parameter exists, and it adds no format or syntax detail beyond the schema. 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?
The description clearly identifies the resource (CDC excess deaths dataset xkkf-xrst) and states its contents: modeled expected vs observed deaths by state and week. It lacks an explicit verb like 'retrieve' or 'query', but the meaning is unmistakable and it distinguishes this from reported-death siblings by emphasizing 'beyond reported COVID deaths'.
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 final sentence, 'Used to estimate true pandemic impact beyond reported COVID deaths,' provides clear context for when this tool is appropriate. It doesn't name alternative sibling tools or give explicit exclusions, but the contrast with reported COVID deaths implicitly routes users away from cdc_weekly_deaths_by_state and similar 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.
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.