Open Country: USDA Section 538 and 515 data

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context beyond annotations: it explains the three maps checked, the eligibility outcomes returned, and the geocoder fallback from Census to OpenStreetMap and FCC.

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 definition is front-loaded with the core action and avoids filler. It is denser than ideal because one long sentence packs program scope, multiple map versions, return fields, and geocoder fallback, but every clause carries relevant information.

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, so the description usefully names the returned eligibility results, matched address, county, place, and data sources. With annotations covering read-only/open-world/idempotent behavior and the schema fully documenting the single parameter, the definition is largely complete, though it could clarify edge cases such as malformed or ambiguous addresses.

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 single address parameter is fully documented with an example in the schema. The description reinforces that it expects one US street address but does not add meaningfully more syntax or formatting detail beyond the schema, so the baseline score of 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?

The description states a specific verb and resource: checking one US street address against USDA Rural Development's ineligible-area map for single family and multifamily housing programs governing Section 538. It also names the exact eligibility outputs, including current, proposed 2020-census, and previous maps, which distinguishes it from sibling tools focused on rentals, income limits, lenders, loan listing, or loan sizing.

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 clear this tool checks one address for rural eligibility, but it does not explicitly say when to use it instead of sibling tools such as find_usda_rural_rentals or size_538_loan. Usage is therefore implied but not routed with alternatives or exclusions.

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, and closed-world, so the safety profile is covered. The description adds genuinely new context: the data vintage (as of October 19, 2026), that only 'active' properties are returned, and that results are paged.

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?

A single dense sentence that front-loads the resource and scope, then enumerates returned fields and closes with the filter/paging note. Every clause carries information, though the field list is long enough to be slightly heavy.

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 no output schema, the description compensates by enumerating the returned fields (name, address, bedroom mix, units, vacancies, restriction end date, etc.), plus data vintage and paging. An agent has enough to call it and interpret results; only ordering/sort behavior is unstated.

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 five parameters are already documented with examples and bounds. The description only restates the optional town filter and paging, adding no syntax or format detail beyond the schema — baseline 3.

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 (find), a precisely scoped resource (active USDA Section 515/514 properties in one county), the data source, and the returned fields. An agent can immediately tell this apart from the 538-program siblings.

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 usage through 'in one county' and 'Optional town filter; paged,' which tells the agent the required scope and the narrowing option. It never states when to prefer this over another tool or when not to use it, though the sibling set (538 income/loan tools) is unrelated enough that no real alternative exists.

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, and closed-world, so the safety profile is covered. The description adds real value beyond that: the calculation basis, the rent-cap formula, the effective date, and the unpaged-vs-paged fallback behavior when no county/area is supplied.

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?

A single dense sentence that front-loads the fiscal year and the core resource before the qualifiers, with no filler. It is long but every clause carries information; it could be split for readability but nothing is wasted.

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 no output schema, the description still conveys what data comes back (limits per household size, per-unit rent cap, project-average cap) and how paging works. Combined with full schema coverage and comprehensive annotations, an agent has enough to call 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 every parameter is already documented in the input schema, which sets the baseline at 3. The description only marginally extends this by framing the rent caps as dependent on household size and tying county matching to the OMB 2023 delineation, but it adds no new format or constraint details.

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 resource (FY2026 USDA Section 538 income limits), the exact basis (115% of AMI, 1-8 persons, effective July 13, 2026), and what else comes back (per-unit rent cap and approximate project-average cap). This clearly separates it from siblings like size_538_loan, list_538_loans, and get_538_lender_table.

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 trailing clause 'Without county or area, lists every area in the state, paged' tells the agent what happens when the optional locators are omitted, which is useful. However, there is no explicit when-to-use guidance, no mention of prerequisites, and no routing to or away from the sibling tools that also deal with 538 data.

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 establish readOnly/idempotent/closed-world, so safety is covered; the description adds real value beyond them with a data snapshot date ('as of October 19, 2026'), the ranking order, and the paged nature of the result. It stops short of noting whether the ranking is stable across pages or how large the underlying table is.

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 resource and identity, then the returned fields, then paging — no wasted sentences. It is a single dense run-on sentence, which slightly hurts scannability but every clause carries information.

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 no output schema, the description correctly takes on the burden of describing return contents: per-lender metrics, aggregate portfolio total, and per-state loan counts. The main residual gap is guidance on page-walking behavior and result-set size, which matters for a paged national table.

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%, with both limit and offset fully documented including ranges and defaults, so the baseline is 3. The description only adds the word 'Paged', which does not extend meaning beyond what the schema already provides.

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 resource ('National Section 538 lender table from USDA's public file'), enumerates the fields returned (loan count, total loan amount, latest fiscal year), the sort order (ranked by loan count), and the extra aggregates (total portfolio, per-state loan counts). This is clearly distinguishable from siblings like list_538_loans or get_538_income_limits, which cover different resources.

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: an agent can infer this is the tool for national lender rankings, and 'Paged' hints at how to walk results. There is no explicit statement of when to prefer this over list_538_loans or find_usda_rural_rentals, and no exclusions or prerequisites.

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 establish readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower, and the description still adds real value: the data vintage ('file as of October 19, 2026'), the result ordering ('newest first'), and the composition of the response. It does not state pagination ceilings or rate limits, but the essentials for a safe read are covered.

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?

A single dense sentence that front-loads the resource and scope before describing the return payload. It is information-rich with no filler, though the long comma-separated field lists make it slightly heavy to parse.

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 no output schema, the description carries the burden of explaining returns and does so by naming the summary metrics and row fields. Combined with the full schema coverage on inputs, an agent has enough to call this correctly; only ordering-vs-offset interaction and hard page caps remain 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 all five parameters are already documented in the schema with examples and bounds. The description only restates the filterable dimensions (lender, fiscal year) and paging, adding no format or edge-case detail beyond what the schema provides. 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?

Presents a specific verb and resource — listing USDA Section 538 guaranteed loans for a single state — and enumerates both the summary aggregates (count, total amount, apartments, tax credit deals, median loan-to-cost, lenders) and the loan-row fields it returns. This clearly separates it from siblings like get_538_lender_table or size_538_loan, which serve different lookups.

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 phrase 'paged and filterable by lender or fiscal year' implies the usage pattern, and the 'in one state' scoping tells the agent the required granularity. However, there is no explicit when-to-use or when-not-to-use guidance, and no sibling tool is named as an alternative when a lender table or loan sizing is what the agent actually needs.

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, and closed-world behavior. The description adds meaningful behavioral context by disclosing the 90%/97% leverage caps, DSCR cap default, 2026 guarantee fees, and that the result is arithmetic rather than a quote.

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 compact and front-loaded with the core action and method. Every phrase adds either scope, computational context, or the important 'not a quote' caveat.

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 12 parameters and no output schema, the description explains the calculation methodology and names outputs such as NOI, debt service, loan-to-cost, and guarantee fees. It could be more explicit about the full return shape, but it is substantially complete for this calculation 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 parameter documentation is already strong. The description adds cross-parameter meaning by explaining how borrower type, lower of cost or value, and DSCR interact in the sizing calculation, going beyond individual field 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 states a specific verb and resource: sizing a USDA Section 538 loan. It also specifies the method and caps, so an agent can immediately distinguish this calculation tool from sibling lookup/list tools.

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 phrase 'Arithmetic on your inputs, not a quote' gives useful usage context, implying this is an estimate/calculation rather than an official quote. However, it does not explicitly say when to use this versus the sibling tools or when it should not be used.

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