Real estate deal memo

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

Goes well beyond the annotations by disclosing cost ($0.75/call), the failure mode when credit is absent (PAYMENT_REQUIRED), the free sample escape hatch, the exact upstream data sources (RentCast), the deterministic nature of the math, and the return envelope. The description's 'computes and returns' framing is consistent with the paid-call semantics behind destructiveHint=true/readOnlyHint=false, so there is no contradiction.

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?

Purpose and strategy scope are front-loaded before the cost and disclaimer clauses, and every sentence conveys distinct information (data sources, metrics, return shape, billing, sample mode). It is a dense single paragraph rather than a segmented structure, which costs it the top score.

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 complex multi-mode underwriting tool with an output schema and fully documented nested assumptions, the description supplies everything an agent needs: what is fetched, what is computed per strategy, billing behavior, and the free sample path. No material decision-relevant gap remains.

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% and the nested assumptions object documents every field with defaults and bounds, so the schema carries the burden. The description restates the three strategy meanings, which the enum already supplies, and adds little new parameter syntax; baseline 3 applies.

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?

States a precise verb and resource ('Underwrite a US residential property from its street address') and immediately enumerates the strategy modes. It clearly delineates itself from the sibling realestate_lookup by describing a full underwriting pipeline (data pull + deterministic metric computation + red flags + memo) rather than a raw record fetch.

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?

Gives strong context: strategy selection is explained in prose, sample=true is offered for a free dry run, and the paid/PAYMENT_REQUIRED behavior is disclosed. However, it never explicitly names realestate_lookup as the alternative to use when only a raw property record is needed, so the sibling routing is left implicit rather than stated.

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

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

Adds behavioral context well beyond the annotations: it discloses the per-call cost ($0.10), the failure mode without credit (PAYMENT_REQUIRED), the sample=true free path, one upstream call per lookup, and the response envelope. The destructiveHint=false read claim is a fetch, which the annotations mark differently, but the description does not assert the opposite of any annotation.

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?

Front-loaded with the core action, then the kind breakdown, then routing, then billing/output in three tight sentences. There is no filler and every clause is decision-relevant.

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?

With an output schema present, the description need not explain return values and still gives the envelope shape. Cost, failure mode, alternative tool, and per-kind payloads cover everything an agent needs to invoke it correctly.

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 restates the kind semantics that the enum already documents and adds only the 'Required unless sample=true' nuance for address, which the schema also carries.

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?

States a specific verb and resource ('Fetch one RentCast record for a US street address') and then enumerates the three distinct record kinds, so an agent knows exactly what comes back for each mode. It also names the sibling tool it is not, which makes the scope unambiguous.

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?

Explicitly routes the agent: 'use realestate_deal_memo when you need all three plus the underwriting' versus one upstream call per lookup, and 'Set sample=true for a free example response'. Both the when-to-use and the escape hatch for a free trial are stated, not implied.

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