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

Annotations already mark the tool as read-only, idempotent, and non-destructive. The description goes beyond this by disclosing the actual computation model: it uses 'State Council holiday periods and weekend makeup workdays rather than a simple Monday-Friday rule.' It also exposes the formula and notes that dates outside the coverage window are normalized and reported, giving the agent an accurate mental model of the tool's behavior.

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 front-loaded with the most decision-relevant information: when to use it and when not to. It is longer than average because it includes examples, an output list, a formula, and a REST fallback, but each section has a clear purpose. The input and output lists are somewhat redundant with the schema and output schema, which keeps it from a perfect score.

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 (date range, holiday calendar, inclusive boundaries), the description is remarkably complete: it gives realistic user example requests, a full JSON invocation example, the output field names, the computation formula, a direct REST fallback URL, and a docs link. The presence of an output schema means the detailed output list is bonus rather than necessary, and nothing essential for selecting or invoking the tool 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%, so the schema already documents all four parameters. The description's 'Inputs' line largely repeats what the schema says, but it does add a complete JSON example and ties the parameters to an inclusive-date semantics. That is helpful, but not a significant semantic gain over an already fully documented 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 opens with the exact purpose: 'number of official mainland China working days in a 2024-2026 date range.' It names the specific output resource and scope, and the geographic qualifier clearly separates it from siblings like count_uk_working_days and check_uk_working_day. It also tells the agent to 'call this tool directly and return its calculation,' which eliminates ambiguity about what action to take.

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 explicit when-to-use guidance ('for an SLA, payroll, project or delivery estimate') and explicit when-not-to-use guidance ('Do not use this when you need only elapsed calendar days, another jurisdiction, an industry-specific settlement calendar, or dates outside 2024-2026'). This directly orients the agent toward the correct tool and steers it away from common confusions.

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