Commercial real estate debt benchmarks — DSCR minimums, LTV maximums, and spread ranges by property type and lender type (bank, agency, CMBS, life company). Source: MBA CREF databook and Trepp public data. For CRE CFOs and capital markets teams structuring financings.
| Name | Required | Description | Default |
|---|---|---|---|
| lender_type | No | ||
| property_type | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark this as read-only and non-destructive, so the bar for additional disclosure is lower. The description adds value by naming data sources (MBA CREF databook, Trepp public data) and explicitly listing the benchmark metrics, without contradicting the annotations.
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 description is three concise sentences, front-loaded with the core purpose, then data source, then audience. Every sentence earns its place with no repetition or filler.
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 read-only benchmark tool with two self-explanatory enum parameters and no output schema, the description covers purpose, metrics, sources, and audience. It could mention the response format (e.g., whether values are medians or ranges), but the listed metrics already imply the output structure.
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?
The schema has 0% coverage and no inline property descriptions, so the description must compensate. It does by naming both parameters ('by property type and lender type') and giving examples of lender types. The enum values are self-explanatory, though the description does not explain each one or note that property_type is required.
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 clearly states the tool returns commercial real estate debt benchmarks (DSCR minimums, LTV maximums, spread ranges) segmented by property type and lender type. This specific verb+resource combination differentiates it from sibling tools like get_real_estate_debt_stress_benchmark or get_mortgage_market_benchmark.
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?
The description specifies the target audience ('CRE CFOs and capital markets teams structuring financings'), which implies when to use the tool. It does not explicitly mention alternatives or when-not-to-use, but the context is clear enough for an agent to select it for financing structuring scenarios.
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.
Each tool targets a specific real estate metric or data source, with detailed descriptions and examples that clearly differentiate them. Even the four climate-related tools serve distinct purposes: composite risk, macroeconomic losses, historical storm tally, and short-term weather scheduling risk. The only potential overlap is between get_noaa_disaster_economics and get_storm_event_history, but their descriptions clarify different use cases.
All 19 tools follow the exact same 'get_' prefix with lowercase snake_case descriptive suffixes. No mixed conventions, no irregular verbs, completely predictable pattern. This makes the tool names easy to learn and reliably distinguishable.
19 tools is on the higher end for a data retrieval server, but the domain encompasses pricing, rents, costs, debt, climate, development, and market metrics, justifying a broad catalog. The four climate tools could arguably be consolidated, but each has a distinct use case and data source, making the count reasonable for a comprehensive real estate benchmark server.
The server covers the core real estate lifecycle: acquisition (cap rates, climate risk), development (construction costs, pro forma), financing (debt benchmarks, mortgage rates), operation (property operating, tax), and market analysis (supply, rents, residential, REITs, NCREIF). Minor gaps exist such as transaction volume data or sub-market specific leasing indicators, but the coverage is extensive for benchmark-oriented use cases.