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

Beyond the annotations (readOnly, idempotent, non-destructive, closed-world), the description discloses the dataset's real limits: pinned MOM coverage only, no employer rosters, no non-Sunday rest days, no bank/exchange closures, plus an explicit rest_day_policy limitation and source_quality/dataset_version provenance fields. It also states the formula and a pinned REST fallback path with a warning not to guess other /api/* routes.

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 text is organized with clear labeled blocks (usage, exclusions, computation, examples, inputs, outputs, formula, fallback, docs) and the usage rule is front-loaded ahead of everything else. It is slightly longer than needed because it enumerates every output field and the formula even though an output schema exists, but no sentence is truly wasted.

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, pinned-dataset lookup the description covers every decision an agent needs: exact scope, hard exclusions, example calls, expected output shape, the underlying formula, and a documented REST fallback with an explicit warning not to guess endpoints. Nothing material is missing given the output schema and annotations already present.

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% and there is a single parameter, so the schema already carries the semantics (Gregorian date, pinned MOM 2026-2027 coverage). The description adds only a restatement ('Inputs: date (date)') and a complete JSON example, which is convenient but not meaningfully beyond the structured fields. Baseline 3 applies.

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?

The description states a specific verb and resource ('Checks a Singapore date using Ministry of Manpower national public holidays'), pins the coverage window (2026-2027), and names the authoritative dataset, so an agent can tell it apart from other territories' check_* tools. It never explicitly distinguishes itself from the sibling add_singapore_working_days / count_singapore_working_days, leaving the singular-date-vs-range split to inference from 'a Singapore date' and the example requests.

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 ('Use this when you need Singapore national public-holiday status for 2026-2027'), when-not-to-use ('Do not use this when you need an employer roster, a non-Sunday weekly rest day, bank/exchange closures, or a year outside the pinned MOM coverage'), and a direct instruction to call the tool rather than answer from memory or stop at discovery. Both the selection condition and the exclusions are spelled out.

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