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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description layers on key behavioral facts: 2027-only calendar scope, deterministic per-division holiday baseline, the exact counting rule, a documented dataset_version/sources return fields, and a hard REST fallback URL with a warning not to guess other paths. That is substantial context 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?

Front-loaded with the when-to-use/when-not-to-use decision, then computation, example, inputs, outputs, formula, fallback, and docs in labeled blocks. It is long, and the 'Inputs:' line largely restates the schema, so it is efficient but not waste-free.

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?

An output schema exists, so return values need not be enumerated, yet the description still names the salient return fields; combined with the formula, fallback endpoint, docs link, and the explicit replacement-day/employer-rule caveat, an agent has everything needed to select and invoke the tool 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 already 100%, so the baseline is 3; the description adds a complete JSON argument example and frames the semantics of the offset ('move one day at a time; decrement remaining only when is_working_day=true'), which goes slightly beyond the schema's bare 'signed offset' wording. It still doesn't explain, e.g., how negative working_days interact with division holidays, so it is not a 5.

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 ('Adds or subtracts dates using the selected Malaysian division's 2027 official public-holiday schedule') and pins the scope to Malaysia/2027, which is exactly what distinguishes it from the ~60 sibling add_*_working_days tools. The example user request ('Add five Kuala Lumpur working days after 2027-02-05') makes the intent 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?

Explicit positive trigger ('use this when you need a deterministic division-specific offset in 2027') and explicit exclusion ('Do not use this when the division is unknown or replacement-day/employer rules matter'). It also instructs the agent to call the tool rather than answer from memory, which is direct invocation guidance.

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