Ferret

Set an insurance limit

save_coverage_limit

Instructions

Records what an insurance policy pays at most — for everything (scope all), one category (jewelry, electronics…) or one tag — optionally for one property, so coverage_check can say when the things it covers are worth more. Without id it adds a limit; with id it replaces that limit (send every field). Amounts in cents. Check coverage_check first so you don't add one twice. Returns the limit with its id.

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": {
      "label": "<label>",
      "limitCents": "<limitCents>",
      "scope": "<scope>"
    },
    "name": "save_coverage_limit"
  }
}

Input Schema

Name	Required	Description
`id`	No	A limit to replace, from coverage_check; leave out to add a new one
`tag`	No	With scope tag: the tag's name
`note`	No	Anything worth keeping: the policy number, a rider
`label`	Yes	The policy line: "Personal property (Coverage C)", "Jewelry & watches"
`scope`	Yes	What it covers: all (everything), category (categoryId) or tag (tag)
`categoryId`	No	With scope category: the category, from list_categories (its subcategories count too)
`limitCents`	Yes	What the policy pays at most, in cents
`propertyId`	No	Only this property's things, from list_locations; left out: every property

Schema Changelog

Changes observed during successful MCP inspections.

Addedv2026.11.10Nov 9, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only say readOnlyHint=false and destructiveHint=false; the description adds the material risk that a replace with id overwrites the whole record ("send every field"), which is effectively a data-loss warning for a partial update. It also discloses the return value (the limit with its id) and the cross-tool read-before-write workflow.

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 write-then-replace distinction and the cross-tool check are front-loaded, and every clause carries information. The single em-dash-heavy sentence is dense, though — the scope enumeration in the middle pushes the key replace warning toward the end.

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?

An 8-parameter mutation tool with no output schema needs its write semantics, return shape, and precondition spelled out; the description supplies all three. Nothing an agent needs to invoke it correctly is missing.

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?

With 100% schema coverage the baseline is 3, but the description goes further by explaining the id field's add-vs-replace semantics, the meaning of each scope value, and that amounts are in cents. It does not cover tag/categoryId/propertyId sourcing details beyond the schema, so not a full 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?

The description gives a concrete verb and resource — it records a policy's maximum payout — and immediately enumerates the three scope variants (all, category, tag) plus the optional property narrowing. It is cleanly distinguishable from coverage_check, its read-side sibling, without opening either 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 states both the when-to-use prerequisite ("Check coverage_check first so you don't add one twice") and the mode switch: no id adds, id replaces. That is explicit routing between two behaviors plus a named alternative tool, leaving little to infer.

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