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

Annotations already establish readOnly/idempotent/non-destructive, and the description goes well beyond them: it discloses the computation formula, the exact output fields, the calendar scope and anniversary-day policy, dataset versioning, a direct REST fallback endpoint with an explicit warning not to guess other paths, and a docs link. This is materially richer than what the structured fields provide.

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 decision rule and organized into labeled sections (usage, exclusion, what it computes, inputs, outputs, formula, fallback, docs). It is on the long side and the formula line plus the full outputs list are somewhat redundant with the output schema, but every section is scannable and nothing is buried.

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 deterministic, read-only calculator with a full output schema, this covers everything an agent needs: trigger, exclusion, date range constraint (2026-2027), argument shape, and a fallback path if the MCP call fails. No missing prerequisite or failure-mode information that would change a correct invocation.

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 baseline is 3; the description adds a consolidated inline signature (with the two booleans marked optional) and a complete JSON argument example that shows all four fields together, which is more useful than the per-field schema examples in isolation.

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+resource ('Counts national working and non-working dates in a New Zealand 2026-2027 range') and pins the scope to national-level holidays. It distinguishes itself conceptually from regional anniversary/employer closures, but never names the obvious siblings (count_* vs check_new_zealand_working_day vs add_new_zealand_working_days), so an agent must infer the split from the name alone.

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 when-to-use ('when you need an auditable New Zealand national working-day count') and when-not ('regional anniversary or employer-specific closures'), plus an instruction to call directly rather than answer from memory. It gives the exclusion condition rather than pointing at the alternative tool by name, so it stops short of full routing guidance.

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