FDA FAERS adverse event signal for a drug — total reports, serious events, deaths, hospitalizations, top reactions with percentages, and signal level (HIGH / ELEVATED / MONITOR / LOW). Source: OpenFDA. Cryptographically attested with a post-quantum signed settlement receipt. Verify at trust.stratalize.com/verify.
| Name | Required | Description | Default |
|---|---|---|---|
| drug_name | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
While annotations already declare readOnlyHint=true and destructiveHint=false, the description adds meaningful behavioral context: it specifies the source (OpenFDA), the inclusion of a cryptographic attestation with a post-quantum signed receipt, and a verification URL. This goes beyond the annotations and informs the user about the response structure's unusual feature, which is valuable.
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, well-structured sentence that front-loads the main output, then adds source and attestation details. It is concise and every clause adds information, though the attestation detail could be considered tangential for some users.
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?
Given the lack of an output schema, the description effectively lists the return components (reports, serious events, deaths, hospitalizations, reactions, signal level). It also mentions the source and verification method. However, it doesn't clarify the input format for drug_name or handle potential edge cases, leaving minor gaps.
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 0%, so the description must compensate. It only mentions 'for a drug' without specifying format (generic vs brand name), case sensitivity, or example values. The parameter name drug_name is self-explanatory but lacks the detail needed for correct invocation.
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 states the tool fetches FDA FAERS adverse event data for a drug and enumerates the specific outputs (total reports, serious events, deaths, hospitalizations, top reactions with percentages, signal level). This is a specific verb (get) with a specific resource (OpenFDA adverse events) and distinguishes itself from the sibling get_drug_adverse_events by mentioning the signal level and attestation.
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 provides no guidance on when to use this tool versus alternatives like get_drug_adverse_events. It doesn't mention use cases, prerequisites, or scenarios where this tool is preferred. The presence of a similarly named sibling makes this omission more significant.
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.
Several tools have overlapping or nearly identical purposes, such as get_drug_adverse_events and get_openfda_adverse_events both pulling FAERS data, get_drug_recall_status and get_fda_recall_history both handling recalls, and get_cms_star_rating overlapping with get_hospital_care_compare_quality. The distinctions rely on subtle source differences or output formatting, making it easy for an agent to select the wrong tool.
All 29 tools follow a strict get_<domain>_<descriptor> pattern, with snake_case throughout. The naming is highly predictable and consistent, which helps agents infer functionality even if they haven't seen a specific tool before.
29 tools is on the heavy side for a healthcare data server, but the breadth of healthcare domains (pharma, providers, payers, supply chain, quality) partially justifies the count. However, the presence of overlapping tools suggests the count could be reduced by consolidation without losing coverage.
The tool surface covers a wide range of healthcare operations: financial benchmarks, drug safety, compliance, quality ratings, provider verification, supply chain, and value-based care. Minor gaps exist (e.g., no specific patient outcome benchmark tool), but overall the core workflows for healthcare intelligence and benchmarking are well represented.