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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the remaining burden is light. The description still adds real value beyond them: the exact formula, the 2026 coverage boundary, the existence of unresolved lunar rules, and the presence of calendar_scope/dataset_version/sources fields that signal data-provenance limits. It stops short of describing error behavior for out-of-range dates.

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-loads the when/when-not guidance and uses labeled blocks that are easy to scan. It is slightly over-long: the 14-field 'Outputs:' enumeration duplicates the existing output schema, and the REST fallback plus docs URLs add bulk that most invocations do not need.

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 one-parameter, read-only lookup with an output schema, everything an agent needs is present: the decision rule, the coverage boundary, the alternative-scope exclusions, a worked example, and a documented REST fallback. Return values are covered by the output schema, so omitting them from prose is correct.

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?

Single parameter with 100% schema description coverage ('Gregorian date in exact 2026 UAE federal-government coverage'), so the schema does the heavy lifting and baseline is 3. The description restates the input as 'date (date)' and repeats the JSON example already present in the schema, adding no new constraint semantics such as what happens for a non-2026 date.

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 precise verb+resource ('checks a UAE date against the federal-government Monday-Friday baseline') and scopes it to 2026 UAE/FAHR holidays. It explicitly carves out the boundary against adjacent cases (Sharjah/local-government, private-employer, bank, exchange, school), which is exactly the differentiation needed in a family of 60+ near-identical check_*_working_day siblings.

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 both sides: 'Use this when you need a UAE federal-government workday or public-holiday result for 2026' and an explicit 'Do not use this when...' list. It also instructs the agent to call the tool directly rather than answer from memory or stop at discovery, which removes a common agent misuse pattern.

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