Skip to main content
Glama

set_probate_route

DestructiveIdempotent

Record what the customer told you about their probate path and their court — the same answers as the Estate page's "Which probate route are you using?" card and the attorney task. Use it when the customer says which path they are using ("we're doing the small estate affidavit", "we're going through full probate", "we'll open ancillary probate in Florida for the condo") or what the court said about needing a lawyer ("the clerk said I need an attorney", "the court said I can file myself", "I'm working with a lawyer"). Their task list follows the answer: a no-court path or an attorney answer sets aside the do-it-yourself court steps, and an attorney answer adds what to bring the attorney. Record only what the customer said, with their words in customer_words; never decide for them which path fits the estate. get_estate_summary shows what is recorded and the path names each state offers. Records the customer's own answer. The estate's tasks follow it: a no-court path or an attorney answer moves the do-it-yourself court steps to Not Applicable and adds attorney-preparation tasks; changing the answer back restores them. An answer about a county SwiftProbate has not verified is sent to SwiftProbate staff for review.

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": {
      "estate_id": "<estate_id>",
      "customer_words": "<customer_words>"
    },
    "name": "set_probate_route"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathsNoThe path(s) the customer says they are using in that state, by the exact names get_estate_summary lists for it, and/or "full_administration" for regular probate (or ancillary probate in another state). An empty list records "not sure yet". Leave this out to change only the attorney answer.
attorneyNoHome state only: what the court told the customer about needing an attorney. 'required' = the court requires one, or they are working with one; 'self' = they can file themselves; 'unsure' = not sure yet. Leave out to keep what is recorded.
estate_idYesThe estate to act on. Call list_my_estates first to get this id.
state_codeNoTwo-letter state the answer is for. Defaults to the estate's home state. Another state only when the estate has an asset there.
customer_wordsYesRequired when marking a task completed or not_applicable, or setting bypasses_probate or has_beneficiary to true: the customer's own words stating that decision, quoted exactly from their message (e.g. "mark this not required", "I paid the filing fee", "it's payable on death to my brother"). Never your own conclusion. If they haven't stated the decision, don't call — ask them.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

Annotations flag destructiveHint=true and idempotentHint=true, but the description carries the real behavioral weight: it discloses downstream effects (do-it-yourself court steps move to Not Applicable, attorney-preparation tasks are added), states reversibility ("changing the answer back restores them"), and warns that an unverified county triggers staff review. It also imposes a provenance rule requiring quoted customer words rather than model inference. This is context an agent cannot obtain from the annotation flags alone.

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

Conciseness2/5

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

Purpose is front-loaded, but the task-effect explanation is stated twice almost verbatim: "Their task list follows the answer: a no-court path or an attorney answer sets aside the do-it-yourself court steps, and an attorney answer adds what to bring the attorney" and later "a no-court path or an attorney answer moves the do-it-yourself court steps to Not Applicable and adds attorney-preparation tasks." The provenance rule is likewise repeated ("Record only what the customer said" / "Records the customer's own answer"), so several sentences do not earn their place in a ~200-word description.

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

Completeness5/5

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

For a destructive, five-parameter mutation with no output schema, the description covers everything an agent needs: valid inputs, what must be quoted versus decided, the side effects on tasks, reversibility, and the escalation path for unverified counties. Nothing about calling it correctly is left to inference.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already defines each of the five parameters, including path naming via get_estate_summary and the attorney enum. The description reinforces the customer_words provenance rule but adds little syntax or format information beyond what the schema states. Baseline 3 applies when the schema does the heavy lifting.

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?

The opening sentence gives a specific verb and resource ("Record what the customer told you about their probate path and their court") and pins the exact scope by naming the UI surface it mirrors, the Estate page's "Which probate route are you using?" card. It also explicitly distinguishes itself from the read-side sibling: "get_estate_summary shows what is recorded." An agent can tell this apart from get_estate_summary and lookup_county_guide without opening a schema.

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

Usage Guidelines5/5

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

It gives concrete trigger conditions with quoted customer utterances ("we're doing the small estate affidavit", "the clerk said I need an attorney") covering both the path answer and the attorney answer, plus a hard exclusion: "Record only what the customer said... never decide for them which path fits the estate." It also routes agents to get_estate_summary for the valid path names and tells them not to call when the customer hasn't stated the decision.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources