Add or count business days

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety. The description adds useful behavioral detail: it skips local weekends (with a specific example for Saudi Arabia) and public holidays, and supports negative add values. This goes beyond the annotation profile, but it does not clarify how holidays are sourced or what happens if both add and end are provided, which is a minor gap but acceptable given the safety covered by 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?

The description is a single sentence that front-loads the action and the two usage modes, then adds the relevant constraints (weekend and holidays). Every clause earns its place—no filler, examples are concrete, and the alternation between add and end is immediately clear. It is an efficient and well-structured description.

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 the tool's moderate complexity (5 parameters, no nested objects) and the availability of an output schema, the description is reasonably complete. It explains the primary modes and key behavior (weekend/holiday skipping) but does not explicitly address edge cases like simultaneous add and end, parameter limits (though these are in the schema), or the exact return value format (which the output schema covers). Overall, an agent can likely call it correctly without further clarification.

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 80%, and the schema already documents start, end, where, and weekend. The description adds semantic value by explaining the two computation modes (add vs. count to end), giving concrete examples for the add parameter (positive and negative), and mentioning the weekend behavior. It does not reintroduce all parameters but enriches the core ones, which is sufficient for an agent to understand their roles without reading the full 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?

The description states a specific verb ('Adds' or 'counts') applied to a clear resource (business days on a date), with concrete examples (add: 10 or -5) and the key behavior of skipping local weekends and public holidays. It is distinct from sibling tools like date_info (date facts) and holidays (holiday lists), so an agent can easily recognize what this tool does without opening its 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 implies when to use the tool (whenever business-day arithmetic is needed) and gives two modes, but it does not explicitly mention alternatives or conditions for choosing this tool over siblings. For example, it does not state 'use holidays to retrieve holiday lists' or 'use date_info for calendar details.' The guidance is inherent but not explicit, leaving some ambiguity about boundary cases (e.g., both add and end provided).

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