Per Patient Day: SNF benchmarks and valuation math

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

Annotations already establish readOnly/ idempotent/ non-destructive/ closed-world, so the description's job is to explain the computation, which it does by listing every output metric including the conditional ones (loan-dependent DSCR/LTV, state-conditional quartile comparison). It does not disclose result formatting, units of the outputs, or the fact that defaults are illustrative rather than market quotes — that caveat lives only in per-parameter schema text.

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?

It is front-loaded and every clause names a real output, but it is delivered as one sprawling ~70-word sentence that mixes input restatement with an eleven-item output list. Splitting inputs from outputs, or trimming the parameter echo, would make it materially easier to scan.

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 12 parameters and no output schema, the return-value enumeration is essential and present, covering both the unconditional metrics and the loan/state-conditional ones. What is missing is modest: units and shapes of returned values, and any guidance on which inputs matter most when a partial answer is desired.

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 schema itself documents all 12 parameters including ranges and default caveats. The description paraphrases only the headline inputs (beds, occupancy, revenue and expense ppd, cap rate, loan, state) and adds no format or interaction semantics beyond what the schema states, so it sits at the baseline.

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 ('the Per Patient Day valuation calculator ... returns patient days, EBITDARM, EBITDAR, rent coverage, NOI, value and value per bed ... DSCR and loan to value') plus the HUD 232/223(f) estimate, so an agent knows exactly what the tool computes. It stops short of naming state_benchmarks, and in fact claims the state cost-report quartile comparison as its own output, so the boundary against the sibling is muddled rather than drawn.

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 enumeration of inputs (beds, occupancy, revenue/expense ppd, cap rate, loan) signals 'use this to underwrite a single SNF deal.' There is no explicit when-to-use, no exclusion, and no statement of how it differs from or complements state_benchmarks even though it duplicates quartile benchmarking. Adequate but inferential.

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 readOnlyHint, idempotentHint and openWorldHint=false, so safety is covered. The description earns credit by disclosing what the payload contains — percentiles, US median, prior-year medians and report count — which is useful behavioral context the annotations cannot convey.

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 purpose and scope before the metric list, and no filler sentences. The long enumeration of metrics is dense but each item is informative, not padding.

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 takes on the job of describing the return payload and does so thoroughly, plus it covers defaults and grouping behavior. The only shortfall is the absence of any cross-reference to the sibling 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 coverage is 100%, so both parameters are fully documented in the schema, including the constraint that national_group applies only when state is US. The description reiterates the state/US/group concept but adds no syntax or edge-case detail 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 resource (Medicare cost-report benchmarks for skilled nursing facilities) and enumerates the metrics returned (occupancy, revenue, margin, payer mix, PPS payment, contract labor). Clear what it produces, but never contrasts with the sibling snf_valuation, so sibling differentiation is left to inference.

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 parenthetical scope '(or the US, or a national ownership or size group)' implies the calling contexts, and the default of US is stated in the schema. There is no explicit when-to-use/when-not guidance or reference to snf_valuation, which is the main alternative an agent would weigh.

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