Get an insurer's verified CY2025 prior-authorization metrics (denial rate, appeal overturn rate, decision times) from its own CMS-0057-F disclosure, plus contract/plan-level rows where collected. Includes source URLs and scope notes.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Insurer slug from list_insurers, e.g. 'unitedhealthcare' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint, idempotentHint, and destructiveHint, so the tool is safe and idempotent. The description adds valuable behavioral context: the data is 'verified', from a specific regulatory disclosure, includes 'source URLs and scope notes', and covers 'contract/plan-level rows where collected'. This goes beyond what annotations provide.
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 sentence that front-loads the main purpose and key metrics. It is informative without being verbose, though breaking it into two sentences could improve readability slightly. Overall, it earns its place without extraneous words.
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 a single parameter, no output schema, and ample annotations, the description provides sufficient context: metrics, source, scope, and included extra data (URLs, notes). It does not specify the return format, but for a simple tool, the description is complete enough for an agent to understand what the tool returns.
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?
The only parameter 'slug' is fully described in the schema ('Insurer slug from list_insurers, e.g. 'unitedhealthcare''). The description does not add new parameter meaning beyond the schema, but the schema coverage is 100%, so the baseline of 3 applies. The description implicitly reinforces the slug source, but that's already in the schema.
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 verb 'Get', the resource 'insurer's verified CY2025 prior-authorization metrics', and specifies the exact metrics included (denial rate, appeal overturn rate, decision times). It distinguishes from siblings like 'get_appeal_rights' (appeals) and 'rank_denial_rates' (ranking) by focusing on a specific insurer's detailed metrics from a particular disclosure.
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 the tool is for retrieving metrics for a specific insurer using a slug, and mentions the data source ('CMS-0057-F disclosure') and inclusion of 'scope notes'. It does not explicitly state when to use versus alternatives (e.g., use 'list_insurers' first), but the context from sibling names and the slug parameter makes the usage reasonably clear.
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.
Most tools have distinct purposes (e.g., get_appeal_rights vs. get_state_external_review), but get_condition_outcomes, get_treatment_outcomes, and get_drug_playbook overlap in the domain of external-review outcomes. An agent may confuse which to use for a given query, especially for drugs that appear in both drug_playbook and treatment_outcomes.
All tool names follow a consistent verb_noun snake_case pattern: get_* for retrieval, list_* for enumeration, rank_* for rankings, and search_* for discovery. No mixed styles or inconsistent verb usage.
Nine tools is well within the ideal 3-15 range. Each tool covers a distinct aspect of the coverage rights domain, and the count feels neither excessive nor thin.
The tool surface covers the core workflow: determining appeal rights, researching outcomes by condition/treatment, accessing insurer metrics, and understanding state processes. Minor gaps exist, such as no direct tool for state comparison or bulk retrieval of all states' external review rules, but these are not critical to the main purpose.