Japan Business Day

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

With no annotations, the description carries the full burden of behavioral disclosure. It discloses a key trait: the cost ($0.01 USDC via x402), which is valuable. However, it does not mention error handling, rate limits, authentication requirements, or whether the operation is read-only (though calculation implies no side effects). It adds some context (settlement/delivery) but lacks deeper behavioral detail.

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 a single sentence that front-loads the core action and purpose, then adds a concise price note. Every word earns its place; there is no filler or redundant repetition of the schema.

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 simple 3-parameter tool with no output schema, the description covers the essential use case and cost. It does not explicitly state the return format (likely a date), but that is implied by the operation. The schema already documents parameter ranges and the calendar enum. The description is sufficient for an agent to call it correctly, though a note on return format would be a minor enhancement.

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 67% (date and calendar have descriptions, but days does not). The description compensates by explaining that 'days' is the number of Japanese business days to add or subtract, clarifying the semantic of the days parameter. It also reinforces the operation's purpose, adding value beyond the schema's enum/type definitions.

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 action ('Add or subtract N Japanese business days from a date') with a specific resource (business days, Japanese) and concrete use cases (settlement T+N, delivery ETA). This distinguishes it from siblings like is_business_day (a boolean check) and list_holidays (listing holidays). The verb-resource pair is specific and 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?

The description provides clear context for when to use this tool (settlement/delivery date calculations) by naming the exact business scenarios. However, it does not explicitly mention alternatives or exclusions (e.g., 'for checking if a date is a business day, use is_business_day'). The guidance is strong but not fully explicit about when not to use it.

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?

With no annotations, the description carries the behavioral burden and does reasonably well: it discloses the calculation logic (same-day before cutoff, else next bank business day) and, unusually and usefully, the cost model ($0.01 USDC via x402). It does not state error handling or the exact return format, hence not a 5.

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 compact sentences: the first frames the question, the second delivers the rule and the price. Front-loaded and waste-free, with only a minor rhetorical lead-in.

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 must convey the return value; it says a value date is returned but not its format (date string, ISO, timezone). Given a zero-required-parameter calculator, the rule, defaults, and price are otherwise sufficient for correct invocation.

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 default cutoff of 15:00 JST but adds no syntax, constraint, or interaction details (e.g., how extraDays composes with the cutoff rule) beyond what the schema already documents.

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 — it returns the value date for a Japanese bank transfer — and the opening question frames the exact scenario. It is clearly distinguishable from generic siblings like add_business_days or is_business_day, though it never names those siblings explicitly.

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 implied by the scenario framing (a bank transfer credit question) and the stated rule, but there is no explicit when-to-use or when-not-to-use guidance relative to alternatives such as payment_due_date or add_business_days. The agent must infer the selection context.

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?

With no annotations, the description carries the full behavioral burden. It does disclose a key trait: paid access at $0.01 USDC via x402, which an agent needs before calling. But it omits return format, error behavior on dates beyond the 366-day cap, and payment failure handling.

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 core action and filters and appends the price last. Every clause (rokuyo, weekday options, use cases, cost) carries information; no 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?

For a 4-parameter, no-output-schema tool, the description covers purpose, both filter dimensions, intended use cases, and pricing. The main residual gap is what the result looks like (list of dates vs. structured objects) and timezone/range semantics, which an agent must infer.

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 four parameters are already documented in the schema, including valid rokuyo values and the date format. The description only echoes examples (taian, sat,sun), adding little beyond the structured fields, so the 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?

Specific verb (find) plus a precise resource (auspicious Japanese dates matching rokuyo and optional weekdays), with the domain concept (rokuyo/taian) named explicitly. An agent can distinguish this from generic business-day siblings like is_business_day or add_business_days.

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?

Use cases (weddings, moving, contracts) imply when the tool is relevant, and it names the two filtering dimensions. However, it never states when NOT to use it or points to the closest alternative (japanese_koyomi), which likely overlaps on rokuyo data, leaving the choice 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?

With no annotations, the description carries the full behavioral burden. It discloses the data source, return elements (holiday name in JA/EN and next/previous business day), and the price ($0.005 USDC via x402). For a read-only check, this is solid context. It does not mention rate limits or side effects, but none are apparent.

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 efficient sentences: the first states the purpose and data source, the second covers return value and price. No filler, all information is relevant, and the core action is front-loaded.

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 simple 2-parameter tool with no annotations and no output schema, the description covers the essentials: purpose, data source, return content, and cost. It does not detail the response shape or error handling, but the schema covers input constraints. It is complete enough for an agent to invoke 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 schema fully documents the 'date' format/range and 'calendar' enum/default. The description adds no extra parameter semantics beyond implying the date is what gets checked. It does not clarify edge cases or how the calendar parameter affects the return. Baseline 3 is appropriate.

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 a specific verb ('Check') and resource ('whether a date is a business day in Japan') and names the data source ('official Cabinet Office holiday data'). It also mentions the return content, which distinguishes it from siblings like list_holidays or add_business_days. The agent can tell what this tool 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 gives the context ('check whether a date is a business day in Japan') but does not explicitly discuss when to use this tool versus alternatives like is_business_day_free or add_business_days. It does not mention exclusions or trade-offs (e.g., the paid tier vs free version). Usage is implied rather than directly guided.

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?

With no annotations, the description carries the behavioral burden and does well: it discloses the data source (Cabinet Office), timezone (JST), date constraint, and bank-calendar semantics. It stops short of stating the exact return value or behavior for out-of-range dates, but the check semantics are mostly inferable.

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 a single front-loaded sentence that wastes no words: it leads with free status, states the core check, then gives the boundary condition and alternatives. Every clause adds decision-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?

For a two-parameter boolean check with no output schema, the description covers scope, data source, calendar variants, and sibling routing. It is slightly incomplete only in not explicitly stating the return type or error/out-of-range behavior, but an agent has enough 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 coverage is 100%, so the schema already documents the date format and the national/bank enum. The description adds beyond the schema by clarifying that the free check is limited to today through 90 days ahead in JST, and that bank mode adds Dec 31-Jan 3 holidays.

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: 'check whether a date ... is a business day in Japan.' It adds clear scope ('between today and 90 days ahead (JST)') and distinguishes this free tool from paid tools for other dates, making its role among siblings clear.

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?

It explicitly says when to use the tool: free checks within the 90-day JST window, and 'For other dates, business-day arithmetic or holiday lists use the paid tools.' This gives agents a direct routing rule for choosing between this tool and its siblings.

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?

No annotations exist, so the description carries the full burden. It does add genuinely useful behavioral context beyond the schema: the tool is a paid operation costing $0.005 USDC via x402. However, it omits anything about what happens on out-of-range dates, error behavior, or why it is read-only.

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 compact sentences that front-load the resource and its returned content, with the pricing appended as a distinct clause. No filler, though the pricing sentence could be slightly tighter.

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 single-parameter lookup with no output schema, the description usefully enumerates the returned fields (rokuyo, era date, lunisolar date, solar terms) and discloses the cost, which is what an agent most needs to call it correctly. Missing only guidance relative to the related lucky-day sibling.

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?

With a single parameter and 100% schema description coverage, the schema already documents the 'date' field and its valid year range (1955-2032). The description adds nothing additional about the date format or semantics, so the baseline 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?

States a specific resource (Japanese traditional calendar for a date) and enumerates the exact outputs: rokuyo lucky days, Reiwa era date, lunisolar date, and 24 solar terms. This is far more informative than the sibling names alone, though it stops short of explicitly distinguishing itself from find_lucky_days_japan.

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?

No when-to-use or when-not-to-use guidance, and no mention of the very close sibling find_lucky_days_japan, which also deals with lucky days. The only contextual signal is the price, which hints at a paid lookup but gives no invocation guidance.

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?

With no annotations, the description carries the behavioral burden and does disclose meaningful traits: T+2 settlement logic, holiday-awareness, and a concrete cost of $0.01 USDC via x402 (payment requirement). It does not explain the return shape or whether the dates are returned as a pair, but the pricing and calendar-convention disclosures are real value beyond the schema.

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 short sentences, front-loaded with the core computation and followed by the settlement caveat and price. No filler; each clause earns its place.

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 one-parameter calculation with no output schema or annotations, the description covers the domain meaning, the settlement convention, holiday-awareness, and the payment model. It could state what exactly is returned (the two dates, and their format) to be fully self-contained, but nothing critical is missing.

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% for the single recordDate parameter, and the schema itself glosses it as 'record date (kenri kakutei-bi) YYYY-MM-DD'. The description adds the semantic that it is a dividend/benefit record date, which is marginal beyond the schema, so the 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?

The description names a specific verb-like computation (last cum-rights trading day / ex-rights date) on a specific resource (Japanese stock dividend record date), which clearly separates it from siblings like jpx_sq_date or jpx_trading_day. It stops short of explicitly naming an alternative sibling, so it is clear but not maximally differentiated.

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 implied by the finance domain (given a record date, derive the settlement-relevant trading dates) and the T+2 settlement note hints at context, but there is no explicit when-to-use statement, no prerequisite, and no comparison against the other date tools in the sibling list.

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?

With no annotations, the description carries the full behavioral burden. It does disclose useful traits: the holiday-adjustment rule for the SQ date and that invocation costs $0.01 USDC via x402. However, it omits the return format, behavior for invalid months, and any error semantics.

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 short sentences, front-loading the core function followed by the pricing note, with no wasted words. It could be slightly tighter but every sentence carries signal.

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 single-parameter deterministic date calculation with no output schema, the description adequately explains what is computed and the governing rule. The absence of a stated output format is a minor gap given the tool's low complexity.

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 'month' parameter is fully documented as YYYY-MM in the schema. The description's phrase 'for a contract month' reinforces the intent but adds no format or constraint detail beyond the schema, so 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?

The description names a specific computed resource (Nikkei 225 futures/options SQ day and last trading day) for an input contract month, and even encodes the underlying rule (2nd Friday, holiday-adjusted). This clearly distinguishes it from generic date siblings like is_business_day, though it never explicitly positions itself against the close siblings jpx_record_date and jpx_trading_day.

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?

There is no when-to-use guidance and no mention of the alternatives (jpx_record_date, jpx_trading_day) or when each is appropriate. The only context offered is the price, which is a cost note rather than a selection cue.

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?

With no annotations, the description carries the full burden. It does disclose a meaningful behavioral trait — the $0.005 USDC x402 payment requirement — which is valuable and not derivable from structured fields. However, it says nothing about return format, error behavior, or whether the extra capabilities (next/previous day, first/last of year) are returned by the same call.

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 question, followed by the extended capabilities and then the price. Three tight sentences with no padding, though the middle enumeration is a slightly loose list.

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 and no annotations, the description partially compensates by enumerating the answers it can produce (open/closed, next/previous trading day, first/last of year). But how those extra answers are triggered by a single date-only parameter is left ambiguous, and no output shape is described.

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%: the single date parameter already documents the YYYY-MM-DD format and the 1955-01-01..2027-12-31 supported range. The description adds no parameter-level meaning beyond the schema, so the baseline 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 names a concrete resource and question ('Is the Tokyo Stock Exchange (JPX) open on a date?') plus additional derived answers, so the agent understands the domain immediately. It does not, however, distinguish itself from siblings like is_business_day or is_business_day_free, leaving overlap in scope unaddressed.

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?

There is no explicit when/when-not guidance and no mention of the obvious alternatives (is_business_day, is_business_day_free, jpx_record_date, jpx_sq_date). Usage must be inferred from the JPX-specific framing alone.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It does disclose a key operational detail: the cost of $0.01 USDC via x402, which is critical for an agent to know. However, it does not mention any other behaviors such as read-only nature, potential errors, rate limits, or authentication requirements. For a simple list operation, the cost disclosure adds value, but other aspects are left to the schema or implicit understanding.

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 extremely concise: a single sentence for the core function plus a separate sentence for pricing. The primary action is front-loaded, and every word contributes to either the function or the cost. There is no wasted text, making it easy for an agent to parse quickly.

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 simple list tool with no output schema, the description gives enough to know the general output (a list of holidays with JA/EN names). It does not explicitly describe the return structure (e.g., array of objects with fields like date, ja_name, en_name) nor mention the 'bank' calendar option, which is a gap given that the tool supports both. It also omits any error or edge-case handling, but given the simplicity, the description is adequate but not rich.

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 schema description coverage is 50% (only 'calendar' has a description; 'year' has none). The description adds little beyond the schema: it says 'for a year' but does not specify the expected format (e.g., integer year like 2024). The 'calendar' parameter is already well-described in the schema, so no extra clarification is needed there. The description does not compensate for the missing 'year' semantics, but it is not misleading either.

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 verb ('List'), the resource ('Japanese national holidays'), and the scope ('for a year'), and mentions the output includes JA/EN names. It distinguishes itself from the sibling tools (which focus on business day calculations) by its explicit listing function. However, it only mentions 'national holidays' while the schema also supports a 'bank' calendar option, which is a slight understatement of the tool's capability.

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?

No explicit guidance is given on when to use this tool versus the alternatives. The description does not mention conditions like 'use this when you need a list of holidays' or exclude cases where business-day tools are more appropriate. The usage context is only implied by the tool's purpose, not 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?

With no annotations, the description carries the behavioral burden; it does disclose the key rule (shifts to previous/next business day on weekends/holidays) and the $0.01 USDC x402 payment requirement. It does not spell out the return value or default calendar, but 'calculator' makes the read-only, pure-function nature clear.

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 tight sentences: purpose, example, adjustment rule, and pricing. Every clause earns its place and the key domain term and behavior are front-loaded.

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 6-parameter tool with no output schema, the description plus a fully documented schema is nearly sufficient. It could explicitly state that the result is a date string and mention the 'none' adjust option, but those are minor given the schema's clarity and the obvious output of a due-date calculator.

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 the baseline is 3, but the description adds a domain example ('month-end close paid end of next month') that clarifies closing='end', payDay='end', and monthOffset=1. That enriches the schema's bare parameter definitions.

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?

Description names a specific resource ('Japanese payment terms (shimebi/shiharaibi) calculator') and gives a concrete example (month-end close paid end of next month). This clearly separates it from sibling tools like is_business_day or add_business_days, which answer different questions.

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 payment-terms example implies when the tool should be used, but the description never explicitly says to prefer it over add_business_days/is_business_day/list_holidays or states when not to use it. That is implied usage rather than active routing.

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