Fix and Flip Loans: flip calculator and lender terms

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real value by enumerating the computed outputs (profit, cash-in, return on cash, 70% rule check, breakeven price), which is the behavioral detail an agent needs since no output schema exists.

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 action is front-loaded in the first clause and the rest is a dense but purposeful enumeration of returned metrics. The long comma-chained list is slightly heavy to parse but every element earns its place as output disclosure.

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 17 parameters and 100% schema coverage but no output schema, the description correctly fills the remaining gap by describing what the calculator returns. Only minor items, such as how lender names are resolved or error behavior when both lender and rate_pct are supplied, are left implicit.

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 every one of the 17 parameters is already documented with defaults, ranges and enums. The description only restates the lender-rate option and lists outputs; it does not add interpretive meaning to any parameter beyond the schema. 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 specific verb and resource ('Runs the fixandflip.loans calculator on a deal') and enumerates the outputs produced, so the tool's function is immediately legible. It does not, however, distinguish itself from siblings like compare_lender_costs or get_lender_terms, which is the main thing keeping it below a 5.

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 clause 'Optionally prices the loan at a listed lender's advertised starting rate' implies usage around the lender parameter, but it never says when to prefer this over compare_lender_costs or how to obtain a valid lender name. There are no explicit when-not conditions or alternative routing.

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?

Annotations already declare this a safe, read-only, idempotent, closed-world operation, so the description needn't repeat that. It adds context annotations cannot: the rates come from lenders' own websites read on 2026-10-24 (a data-freshness caveat), that results are ranked by profit, and that leverage, points and fees are held constant across lenders. It does not mention lender coverage or what happens when no lender matches the state filter.

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?

Two dense sentences that lead with what the tool produces and its ranking criterion before covering the optional filter. Nothing is wasted, though the parenthetical '(plus those to check)' is slightly cryptic and the second sentence carries less weight than the first.

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 16 parameters, no output schema and read-only annotations, the description carries the burden of describing the result, and it does: interest cost, total financing and profit per lender. It also flags rate provenance and date. What's missing is what the comparison does when a lender cannot fund the deal (e.g. LTC/ARV cap failures), which matters for a 16-parameter comparison tool.

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 all 16 parameters are already documented with defaults, ranges and examples; the baseline is 3. The description adds a little beyond that, clarifying that the agent's own leverage/points/fee inputs are applied uniformly to every lender and that state acts as a filter with a 'to check' fallback, but it does not explain any individual input.

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: it prices one flip at every listed lender's advertised fix-and-flip start rate and ranks results by profit. The scope (multi-lender comparison vs. a single scenario) implicitly separates it from calculate_flip_profit, but no sibling is named explicitly. An agent can still tell what it does without opening the schema.

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 implies the situation (you have one flip's numbers and want to see which lender is cheapest) and explains the effect of the optional state filter, including the nuance that non-listing lenders are kept as 'those to check'. It never states when to prefer calculate_flip_profit, get_lender_terms, or find_lenders instead, so routing between siblings is left to inference.

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?

It provides crucial operational traits not covered by annotations: the external source (fixandflip.loans), the data freshness/cut-off date (read 2026-10-24), and the specific fallback behavior ('check') when a lender publishes no state list.

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 perfectly sized. It is highly efficient, front-loading the data source and specific attributes without unnecessary 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?

Given the detailed schema and clear annotations, the description provides all necessary context—source, scope, data attributes, and error/edge case handling—making it maximally complete for this tool.

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?

Since schema coverage is 100%, the baseline is 3. However, the description significantly improves semantic understanding by detailing the specific data points returned for each lender (starting rate, leverage, etc.), giving the agent context about the quality and type of data found.

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 goal: listing hard-money and DSCR lenders. It specifies the resource (fixandflip.loans) and distinguishes this tool's function from sibling tools by focusing on lender discovery rather than calculation or specific term retrieval.

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?

While it doesn't explicitly list alternatives, the context of 'finding' lenders implies it should be used when a list of providers is needed, effectively differentiating it from tools focused on calculation or comparison of terms.

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?

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds real context beyond them: the data is a static snapshot captured on a specific date ('read 2026-10-24'), sourced from each lender's own website, and includes exact source pages for verification. It omits any note on how stale data should be treated or what a miss looks like.

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?

One front-loaded sentence that states what is returned, the source, and the capture date before the field list, with zero filler. The enumeration, while long, earns its place by telling the agent exactly what coverage to expect.

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?

There is no output schema, but the description compensates by enumerating the returned fields (rates, leverage, points, terms, credit rules, loan sizes, states, license, notes, source pages). Combined with annotations covering the safety profile and the description covering provenance and freshness, an agent has enough to call it correctly; only the failure/empty case is unaddressed.

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 coverage is 100% and the single 'lender' parameter already carries example values (Kiavi, Lima One, RCN Capital). The description contributes only the framing that the name identifies a lender whose own site was scraped, which adds little beyond the schema; 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 specific verb and resource ('Everything fixandflip.loans recorded from one lender's own website') and enumerates the exact fields returned, so an agent knows this is a single-lender detail lookup rather than a search. It does not explicitly name siblings like find_lenders or compare_lender_costs, so the differentiation is implied by 'one lender' rather than stated.

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?

Usage is only implied: the phrasing and the required 'lender' parameter make it clear this is for pulling detail on a lender you already have a name for, but there is no explicit when-to-use, when-not-to-use, or pointer to the sibling search/compare tools. An agent must infer the routing from context.

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