Business-day arithmetic honoring weekends + regional holidays. operation: add_business_days (needs days, negative ok) | count_business_days (needs end_date, inclusive) | next_business_day | previous_business_day. region: US | UK | EU | NONE. custom_holidays: list of YYYY-MM-DD.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | ||
| region | No | US | |
| end_date | No | ||
| operation | Yes | ||
| start_date | Yes | ||
| custom_holidays | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses that weekends and regional holidays are honored, and that count_business_days is inclusive. However, it does not specify return types (date string vs integer count) or the default region behavior, leaving ambiguity for the agent.
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 information-dense, but the run-on format with pipes and inline requirements makes it slightly dense and harder to scan. Still, it communicates a lot in few words without 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?
This is a complex tool with six parameters and multiple operations, no output schema, and no annotations. The description covers operations, required parameters, and holiday formatting well, but lacks examples, return value descriptions, and edge-case behavior (e.g., invalid dates), leaving it almost complete but not fully self-contained.
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 has zero parameter descriptions, and this description fully compensates: it explains the role of operation, days (negative allowed), end_date (inclusive), region options, and custom_holidays format. Every parameter is meaningfully described.
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 clearly states the tool performs 'Business-day arithmetic honoring weekends + regional holidays' and enumerates specific operations (add, count, next, previous). This unambiguously distinguishes it from sibling tools like currency_convert or loan_amortization.
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?
Provides clear context on usage: it is for business-day calculations. It also details operation-specific requirements (e.g., add_business_days needs days, count_business_days needs end_date). However, it does not explicitly mention alternative tools or conditions when this tool 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.
Add one secure layer between your agents and this server.
Each tool targets a distinct calculation domain: business days, SaaS metrics, compound growth, FX, depreciation, IRR, NPV, loans, and batch execution. The only closely related pair (IRR and NPV) is clearly differentiated by descriptions.
Most tools use snake_case, but the pattern is mixed: calculate_metric and list_metrics are verb-first, currency_convert is verb-last, batch_calculate starts with a modifier, and the rest are noun phrases like loan_amortization and net_present_value. This inconsistency could cause minor confusion but remains readable.
11 tools is well within the typical range for a specialized calculator server. Each tool covers a distinct area, and the auxiliary tools (list_metrics, batch_calculate, health_check) support the core set without bloat.
The server covers a broad swath of business/finance calculations: time-value-of-money (NPV, IRR, compound growth), loans, depreciation, currency, business days, and SaaS metrics. Minor gaps exist (e.g., no general unit conversion or statistical functions), but for the stated purpose the surface is complete.