Skip to main content
Glama

Appeal Draft – Twin Cities property tax appeal

Is my property tax assessment too high? Should I appeal? (Twin Cities, Minnesota)

check_property_assessment
Read-onlyIdempotent

For one home in the Minneapolis-Saint Paul area: the county's estimated market value, what recorded sales of similar nearby homes say it is worth, the gap between them, whether an appeal looks worth filing, the yearly tax a cut would save, and the county's appeal steps and 2027 dates. Use for 'is my property tax assessment too high', 'should I appeal my property value', 'my assessment went up, is it fair', 'what is my house assessed at vs what it would sell for'. Covers houses and townhouses in Ramsey, Anoka, Dakota, Scott and Washington counties and the City of Minneapolis; any other address gets an honest 'not covered'. Pass the street address with its city or ZIP. If the user has a newer valuation notice, pass its estimated market value as value_on_notice. Returns a link that opens the comparison on appeal-draft.vercel.app already filled in for that home.

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": {
      "address": "<address>"
    },
    "name": "check_property_assessment"
  }
}

Input Schema

NameRequiredDescriptionDefault
zipNo5-digit ZIP, if not in the address
cityNoCity, if not in the address
addressYesStreet address, ideally with city and ZIP, e.g. '1852 Ashland Ave, Saint Paul, MN 55104'
value_on_noticeNoOptional: the estimated market value printed on the owner's newest valuation notice, used instead of the value on our roll

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds context the annotations cannot: the geographic coverage boundary, the graceful 'not covered' outcome for out-of-area addresses, and the fact that the result is a pre-filled link to an external site (appeal-draft.vercel.app). It stops short of describing failure behavior for malformed or ambiguous addresses.

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?

Front-loaded with the deliverable list, then use cases, coverage, input guidance, and return format — a sensible order with no filler sentences. It is dense and somewhat run-on, with a long comma-separated output enumeration, but nearly every clause carries information the agent needs.

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?

With no output schema, the description still closes the loop by stating the return value (a pre-filled link on appeal-draft.vercel.app). Combined with explicit coverage limits, input-passing guidance, and the optional notice value, an agent has everything needed to decide to call it and to call it correctly.

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 100%, so the baseline is 3, but the description adds real meaning: it says to pass the street address with its city or ZIP (explaining why the optional city/zip fields exist), and it gives the trigger condition for value_on_notice — the user has a newer valuation notice — which is more actionable than the schema's 'used instead of the value on our roll'.

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 names a specific subject (one home in the Minneapolis-Saint Paul area) and enumerates exactly what comes back: county estimated market value, comparable-sales value, the gap, appeal-worthiness, tax savings, and appeal steps/dates. An agent can distinguish this per-home analysis from the sibling 'property_tax_appeal_dates' (dates only) and 'assessment_ratio_by_area' (area-level ratios) without opening any 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?

It supplies concrete trigger phrasings ('is my property tax assessment too high', 'should I appeal my property value') and an explicit exclusion boundary: houses and townhouses in five named counties plus Minneapolis, with anything else returning an honest 'not covered'. It also tells the agent when to supply value_on_notice. The only gap is that it never explicitly routes to a sibling for date-only or area-ratio questions.

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.