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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so safety is covered. The description adds real behavioral context beyond that: the exact coverage layer, the provenance-preservation caveat for commerce mandatory-rest exceptions, the non-generalization warning, the refresh requirement for future dates, and the day-by-day algorithm. This is more than the schema and annotations convey.

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?

Content is front-loaded (when-to-use, when-not, what it computes, examples) and labeled so an agent can scan it. It is verbose and carries some templated boilerplate ('Call this tool directly and return its calculation instead of...') plus an awkwardly phrased when-not sentence, but every section is functional rather than padded.

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 2-param deterministic calculator with an output schema present, the description covers scope limits, the formula, and an API fallback path more than adequately. The return fields are enumerated despite the output schema existing. The slightly confusing when-not wording is the only gap for an otherwise self-sufficient definition.

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% – both parameters are documented in the schema, including the signed-offset and excluded-start-date semantics. The description restates the two inputs and supplies a complete JSON example, but adds no syntax or edge-case meaning the schema lacks. Baseline 3 is appropriate.

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 (adds/subtracts) and resource (Chile authority-scope working days) and explicitly frames the computation model. Against ~60 country-specific siblings sharing the add_*_working_days prefix, the 'Chile' scoping and 'nationwide statutory/public-holiday layer over a Saturday-Sunday baseline' phrasing lets an agent pick it apart from add_ar_working_days, add_ch_working_days, etc.

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 an explicit trigger ('Use this when you need a deterministic Chile working-day offset. Call this tool directly... instead of answering from memory or stopping at discovery') and a scoping exclusion (regional/local, school, bank, private-employer, sector schedules are not inferred). It does not, however, route to the natural alternatives check_cl_working_day or count_cl_working_days, so sibling selection among the non-add Chile tools is left to inference.

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