Business Day Calendars

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

Annotations only declare readOnlyHint and openWorldHint; the description goes well beyond them by disclosing the payment mechanism (x402 on Base, $0.001 USDC per call), the rate limit (first 5 calls/day/client free), determinism ('no AI'), and that skipped holidays are returned. For an agent that must decide whether a paid call is warranted, this is exactly the extra behavioral context needed.

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 sentences, no filler. Core semantics lead, the pricing/rate-limit facts follow, and every clause (negatives, calendars, skipped holidays, cost) carries information an agent needs before invoking.

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 3-param stateless computation with no output schema, the description covers purpose, calendar semantics, return content, determinism, and cost, which is close to sufficient. It omits error/boundary behavior (e.g., what happens with an invalid calendar alias), leaving only minor gaps.

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 genuinely adds meaning the schema does not: it makes explicit that negative 'days' values subtract rather than error, and frames the calendars argument as a joint-calendar AND semantics. It does not add format/alias detail 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?

States a specific verb+resource (add/subtract N business days to a date), clarifies that negative days subtract, and names the joint-calendar scope (NYSE, Fedwire/FedACH, TARGET2, UK). It lets an agent distinguish this from business_days_between and settlement_date, but it never names a sibling directly, so it falls short of the 5 bar.

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 guidance and no routing to siblings such as adjust_date or settlement_date, which are the closest alternatives. The pricing/free-tier sentence tells the agent the cost of calling, not when to choose this tool over another.

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 cover only readOnlyHint and openWorldHint; the description adds genuinely new behavior: deterministic/no-AI execution and a concrete cost model ($0.001 USDC per call via x402 on Base, first 5 calls/day per client free), including an implicit rate limit. It omits what happens under modified conventions when consecutive days are closed, but adds real value beyond the annotations.

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 scope are front-loaded in the first clause, conventions follow, then use cases, then pricing. Every sentence earns its place with no filler or redundancy.

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 small, deterministic, read-only computation tool with no output schema, the description covers purpose, conventions, calendars via schema, use cases and cost. It could note the return value shape (the adjusted date), but nothing an agent needs to select or call the tool correctly 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% and each parameter, including calendar aliases and the convention default, is documented in the schema. The description merely repeats the four convention names already listed in the schema and adds no semantics (e.g. how modified_following differs from following), 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?

Specific verb+resource: it states that it rolls dates landing on weekends/holidays using a named business-day convention, and lists the four conventions. It implies but never explicitly distinguishes itself from close siblings like is_business_day (check only) or add_business_days (shift by N), so it falls short of 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?

"Typical for payment, coupon and invoice due dates" gives domain context for when it is appropriate, which is more than nothing. It gives no when-not guidance and never routes the agent to a sibling tool such as settlement_date or is_business_day, so usage remains implied rather than explicit.

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?

Goes well beyond the readOnly/openWorld annotations by disclosing a hard bound (max 10 years), determinism ('no AI'), the return shape (count plus weekday holidays in range), and commercial behavior (x402 USDC pricing, 5 free calls/day/client). Cost and rate-limit disclosure is exactly the context an agent needs before calling.

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 computation semantics and efficient overall, with each sentence carrying distinct information. The trailing pricing/limit clause is relevant but slightly bulky relative to the rest.

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 explains the return value (count, sign behavior, holiday list) and adds the operational constraints. An agent has everything needed to call it correctly and predict the result.

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; the description adds the counting convention itself — 'days after start up to and including end (inclusive=true also counts start)' — which clarifies what the two required date params actually compute. The calendars param semantics (joint intersection) are left entirely to the schema.

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 ('counts business days between two dates') and pins down the exact counting convention (days after start, up to and including end) on a joint calendar. The semantic detail is enough to distinguish it from add_business_days or is_business_day without opening a 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?

Usage is implied through the counting semantics (inclusive flag, negative result when end < start), but no sibling is named and no when-to-use/when-not guidance is given. It also doesn't say which calendar to pick versus list_holidays or settlement_date workflows.

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 cover only readOnlyHint and openWorldHint, but the description adds genuinely useful context the annotations cannot: deterministic/no-AI behavior, per-call pricing ($0.001 USDC via x402 on Base) with a free tier, and what information comes back (holiday name, NYSE early closes, prior/next business day). That is real behavioral disclosure beyond structured fields.

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?

Three tight sentences: the core semantics first, then determinism, then cost. Every sentence carries information, though the calendar list in the first sentence partly duplicates 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?

No output schema exists, so the description usefully enumerates what the call returns (holiday, early closes, adjacent business days) and discloses the payment model. This is close to complete for a two-parameter predicate 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% and both parameters are fully documented there, including aliases and the all-calendars-must-be-open rule. The description only restates the calendar names, adding no syntax or format 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 predicate over a date and enumerates the calendars it applies to, making the operation unambiguous. It does not explicitly contrast itself with siblings like business_days_between or settlement_date, so it falls short of the top score.

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 alternatives among the six sibling date tools. The agent must infer from the name alone whether this is the right tool versus business_days_between or settlement_date.

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?

Beyond the readOnly/openWorld annotations, the description discloses meaningful behavior: deterministic/no-AI execution, explicit omission of weekend-only holidays, the 1 pm early-close detail, observance/substitute rules, and the x402 USDC payment model with a free tier. This is exactly the kind of context annotations cannot carry.

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 'what it lists' clause, then caveats, then pricing. Dense but every sentence carries information; the pricing/payment sentence is the only part that could be seen as tangential, though it is operationally 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 no output schema, the description does the work of describing return content (full closures, early closes, observance rules) and payment/auth requirements. It is complete enough to invoke correctly, though it never states the response shape (structured list vs. text) explicitly.

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 already 100%, so the baseline is 3, but the description adds value by naming the holiday families each calendar code denotes and restating the supported year range, which helps the agent map 'XNYS' or 'UK-ENG' to real semantics rather than guessing from the bare enum-less example.

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 gives a specific verb ('Lists') and resource ('closing days for one calendar and year') and enumerates exactly what the list contains per calendar family (NYSE full closures and 1 pm early closes, Fedwire/FedACH holidays, TARGET2, UK bank holidays). It does not name or contrast any sibling, but the resource is specific enough to distinguish it from the business-day-math siblings at a glance.

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 — call it to retrieve holiday/closing-day lists — and the 2000-2099 year bound is stated, but there is no explicit when-to-use vs. when-not guidance and no reference to the sibling tools (is_business_day, business_days_between) that an agent might weigh it against.

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 only cover safety (readOnly/openWorld), and the description adds substantive behavior beyond them: the trade-date roll rule, determinism ('no AI'), the x402 payment model at $0.001 USDC per call on Base, and a 5-calls-per-day free quota per client. Pricing and rate-limit disclosure is exactly the extra context annotations cannot carry.

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?

Three tight sentences, front-loaded with the core computation before defaults, roll behavior, and pricing. No filler, though the billing/quota sentence is somewhat commercial noise relative to the agent's selection decision.

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 deterministic date-arithmetic tool with no output schema, the description covers defaults, calendar semantics, roll behavior, and cost. It omits the return shape (a date string) and the legal values for the calendar identifier, but those are minor for a three-parameter read-only 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% (t, calendars, trade_date all documented with examples and ranges), so the schema already carries the parameter burden. The description adds semantic meaning for t=1 (US equities since 28 May 2024) and the default calendar pair, but that largely restates schema content, matching the 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+resource: computes a settlement date T+N from a trade date on a joint calendar, and names the roll-forward convention. However it never explicitly distinguishes itself from the close sibling add_business_days, which on a single calendar would do almost the same arithmetic, so the agent must infer the difference from the calendar/lag framing.

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 useful context for using the defaults ('t=1 (US equities since 28 May 2024)', default XNYS,FED) and describes the roll-to-next-business-day precondition. It does not say when to prefer this over add_business_days/is_business_day, nor name any exclusion, so usage is implied rather than prescribed.

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