PolicyVera insurance quotes

Confirm what PolicyVera read

confirm_policy_document

DestructiveIdempotent

The person's own confirmation of a read policy, through PolicyVera's own confirm route, in two calls. The first records nothing: it answers ready with willConfirm, every value it would record (the person's own answers from their last confirmation when they confirmed it before, else what PolicyVera read, with the person's corrections over them), and a confirmId; or it asks first what PolicyVera's confirm page asks first (whether the document is their policy, the kind of policy). The second, with the same arguments (corrections, policyType, isMyPolicy), the confirmId and personConfirmed: true, records them. The confirmed values reach the insurance agents on the person's open requests for that line.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "documentId": "<documentId>"
    },
    "name": "confirm_policy_document"
  }
}

Input Schema

Name	Required	Description
`confirmId`	No	From the first call on these same values; with personConfirmed it records them.
`documentId`	Yes
`isMyPolicy`	No	Only when the first call asked whether this is the person's current policy, and they said it is.
`policyType`	No	Only when the first call asked the kind of policy: the person's answer, from policyTypeOptions.
`corrections`	No	Only the values the person corrected.
`endedAnswer`	No	Only when the first call asked about an ended policy (ended) and the person said it lapsed: PolicyVera files it as a previous policy and the request for this line goes without current coverage, as the site's own answer does. The reply's endedAnswered says it in the site's words; then show willConfirm and confirm as usual.
`personConfirmed`	No	Only after the person saw every line of willConfirm and said yes.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 4, 2026

TDQS

A4.5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already flag non-read-only, destructive, open-world and idempotent behavior; the description adds substantive detail about what is recorded in each call, that the first call is a no-op, how corrections overlay prior answers/read values, and that confirmed values reach insurance agents on open requests. This is exactly the kind of behavioral context annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded and information-dense with little repetition; every sentence serves the two-call protocol and impact. However, the long nested clauses and parentheticals make it harder to parse than necessary for a multi-step tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex, state-changing two-call tool with no output schema, it covers the key flow, return cues, and downstream effect well. It leaves minor gaps around how to obtain documentId and error/permission handling, but annotations and the schema cover much of the rest.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is high (86%), so the schema carries most field-level meaning, but the description adds cross-parameter flow semantics: confirmId comes from the first call on the same values, personConfirmed only after the person saw every line, and isMyPolicy/policyType depend on questions the first call asked. It does not explain documentId sourcing or every correction field, keeping it just short of a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource—the person's own confirmation of a read policy—and frames it as a two-call confirm route that records values. The read/confirm distinction and downstream effect make the purpose identifiable without opening a sibling schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explains the two-call sequence clearly: the first call records nothing and returns ready/willConfirm/confirmId or asks the site's first questions; the second call with personConfirmed records. Conditions for isMyPolicy and policyType are tied to what the first call asked, but it never explicitly routes an agent from read_policy_document or states when not to use this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All PolicyVera insurance quotes tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?