CDC FluView state-level influenza surveillance (vh55-3he6). Returns weekly ILI (influenza-like illness) activity levels per state.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max rows (default 50) | |
| season | No | Flu season (e.g. '2023-24') | |
| statename | No | Full state name |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, covering the safety profile. The description adds useful context about the data source and output granularity, but it does not disclose behaviors such as pagination, data freshness, season defaults, or how missing state names are handled.
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?
The description is a single dense sentence that immediately identifies the source and result, includes the dataset identifier, and has no filler or repeated schema information. Every clause 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 read-only tool with three optional parameters and no output schema, the description provides the essential context: source, dataset ID, geographic scope, and return semantics. It could additionally describe the shape or scale of the activity levels, but the current description is largely sufficient for selection and basic 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 description coverage is 100%, so limit, season, and statename are already documented. The description reinforces the state-level and weekly nature of the data but adds no new parameter-level details beyond what the schema provides, 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 names a specific source (CDC FluView), a specific dataset (vh55-3he6), and a clear result (weekly ILI activity levels per state). This clearly distinguishes it from the many other cdc_* siblings, which cover different topics like deaths, vaccinations, or general dataset queries.
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 implies this tool is for state-level flu surveillance data, but it does not explicitly state when to prefer it over alternatives like cdc_dataset_query or other CDC tools. There are no exclusions or explicit when-not-to-use conditions, so the agent must infer applicability from the wording.
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.