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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the description's burden is lighter. It still adds real behavioral context: the exact computation scope, the calendar profile/dataset version and substitute-day policy outputs, and a REST fallback endpoint so the agent does not guess a path. It stops short of explaining how non-working days are classified beyond the formula line.

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 definition is front-loaded with the use/no-use decision, which is good, but it is padded: the 'Inputs' list and 'Complete JSON argument examples' duplicate the input schema, and the 'Formula' line ('working_days += Canada federal status.is_working_day') is effectively filler that conveys nothing usable.

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 a rich output schema, the description need not enumerate return fields, yet it does list them all, so nothing an agent needs is missing: jurisdiction limits, date-range bounds, include flags, fallback endpoint, and docs link are all present. Slight redundancy against the output schema costs it the top mark.

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, setting the baseline at 3. The description restates the inputs with types and repeats a full JSON example that the schema's 'examples' block already contains, adding convenience but no new semantic meaning (e.g., no clarification of boundary ordering or DST-like edge cases).

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 (counts) and resource (Canada federal working/non-working dates) with explicit jurisdiction and a pinned year range (2026-2027). It differentiates from provincial/private-employer semantics, but does not distinguish itself from the near-identically named sibling add_canada_federal_working_days, which an agent could easily confuse it with.

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?

Explicitly says when to use it ('auditable Canada federal baseline count for a pinned year'), instructs to call it directly rather than answering from memory, and gives an explicit exclusion ('Do not use this when you need provincial, private-employer or schedule-specific substitute-day semantics'). This is a textbook when/when-not statement.

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