Look up property tax rates and estimated annual taxes for any county or city. Essential for calculating holding costs in rental and flip analysis. USDV Capital — Your Real Estate CFO.
| Name | Required | Description | Default |
|---|---|---|---|
| state | Yes | State | |
| county | Yes | County or city name | |
| propertyValue | No | Property value for tax estimate |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds no further behavioral context such as data source, geographic coverage limitations, or response format. The claim 'for any county or city' is an overstatement without caveats, and the marketing tagline adds no behavioral insight.
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 first two sentences are front-loaded and efficient, but the third sentence 'USDV Capital — Your Real Estate CFO.' is pure marketing and does not earn its place for an AI agent. It is not verbose, but every sentence should serve tool selection and invocation; this one doesn't.
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?
For a simple lookup tool with 3 parameters and no output schema, the description indicates what the tool returns ('rates and estimated annual taxes') and its use case. It lacks explicit mention of output units, tax year, or data freshness, but for the agent's selection purpose it is reasonably complete.
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?
Schema description coverage is 100%, so the baseline is 3. The description reinforces that 'county or city' maps to the county parameter and that propertyValue is used for estimates, but it does not add new semantic meaning beyond the schema's existing descriptions.
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 opens with a specific verb and resource: 'Look up property tax rates and estimated annual taxes for any county or city.' This clearly distinguishes it from sibling tools like util-rent_estimate or util-insurance by focusing on property taxes. It is not a tautology or vague statement.
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?
It provides clear usage context: 'Essential for calculating holding costs in rental and flip analysis.' This tells the agent when to select this tool over others. It does not explicitly list exclusions or alternative tool names, but the context is sufficiently clear for a utility tool.
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 clearly distinct purposes, especially the calculators and utilities. The markets-* group has five tools that all return market data, but each has a distinct focus (compare, nearby, screener, search, stats) with descriptions that clarify the differences. Overall, an agent can generally tell them apart, though the market tools could still cause minor confusion.
The naming convention is consistent across categories using lowercase with hyphens and a prefix (action-, calc-, deal-, eligibility-, markets-, util-). Within categories there is slight inconsistency, such as action-consultation (noun) vs action-prequalify (verb) vs action-send_report (verb_noun), but the overall pattern is predictable and readable.
With 23 tools, the server covers a broad range of real estate CFO services: property analysis, market intelligence, eligibility, and client actions. This is slightly on the heavy side but each tool serves a distinct purpose within the domain. It could be trimmed, but the count is not unreasonable given the scope.
The tool set covers the core lifecycle of a real estate deal: market research, property-level analysis, calculators for various strategies, eligibility checking, and client engagement actions. Minor gaps exist—such as no tool for tracking existing deals or a general mortgage payment calculator—but the main workflows are well supported. Completeness is strong for the stated purpose.
