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

Annotations already mark the tool as read-only, open-world, and idempotent, so the description's job is to add context. It does: it reveals the dependency on RentCast data, the cost of $0.75 per call, the PAYMENT_REQUIRED failure mode, and the 'not financial advice' caveat. It also states the return shape ({data, sources, as_of, confidence, notice}). These are valuable behavioral disclosures beyond the annotations, though it doesn't detail what happens when data is missing for an address. No contradiction with 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 moderately long but every sentence adds value: purpose, data sources, metrics, return shape, caveat, cost, and sample mode. It is front-loaded with the core action, then expands logically. It is not bloated or redundant; it compresses a lot of information into a few sentences. Slightly verbose but well-structured, hence a 4.

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 tool with 5 top-level parameters (one nested with 18 sub-fields), an output schema, and external data dependencies, the description is remarkably complete. It covers what the tool does, how inputs affect outputs, what the response contains, the cost, the sample mode, and the caveat. The only details left to the schema are per-parameter defaults and bounds, which are appropriately delegated. An agent has enough information to decide when to call it, what inputs to provide, and what to expect in return.

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 input schema already provides 100% coverage with detailed descriptions for every parameter, including defaults and bounds, so the baseline is 3. The description adds meaning by explaining how parameters influence the computation (e.g., 'computes NOI, cap rate, cash-on-cash, DSCR, GRM and break-even occupancy from stated assumptions' and '70%-rule, profit and ROI for a flip'), clarifying the role of strategy-specific assumptions. It also notes that all assumptions are optional with documented defaults, which aligns with the schema. This goes beyond a simple restatement, earning a 4.

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 ('Underwrite') and a clear resource ('a US residential property from its street address') and enumerates exactly what it does: pulls property data, computes financial metrics, lists red flags, and returns a structured result. It also names the strategy variants (rental/flip/hold), which distinguishes it from the sibling realestate_lookup that presumably only retrieves property details. No ambiguity about the tool's core function.

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 makes the intended use explicit ('for a rental, flip or hold strategy') and even gives guidance on the sample mode ('Set sample=true for a free example response') and payment requirement. It does not, however, explicitly state when to prefer this over the sibling realestate_lookup or when not to use it, though the purpose is so distinct that the alternative is obvious. The cost and sample notes are practical usage guidance, so this is a 4 rather than a 3.

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