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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description only needs to add behavioral context - and it does: it discloses the exact formula, that temporary fuel-conservation closures apply to government offices only and were cancelled April 8, and that essential services, schools, private employers, sector agreements and unlisted notices are NOT inferred. This meaningful 'what is not covered' disclosure exceeds what the annotations 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?

The description is front-loaded with a usable opening sentence, but the 'Do not use this when...' sentence is garbled and several sections (Formula, Outputs field list, REST fallback, Docs link) add bulk. The restated output-field inventory is largely redundant given the output schema exists. The dense caveat list earns its place, but the overall size is disproportionate to a single-date check.

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 date check with a full output schema and rich annotations, the description supplies the needed context: what is computed, the formula, the calendar scope, and the explicit non-inferences. Listing output fields is unnecessary given the schema, but nothing an agent needs in order to call it correctly is missing.

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% for the single 'date' parameter, so the schema already documents format and examples. The description restates 'Inputs: date' and adds two complete JSON argument examples, which adds minor convenience but no semantics beyond the schema. 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: it checks a date against a Saturday-Sunday weekend baseline and exact 2026 Sri Lanka authority events, returning a working-day result. The country-specific scope (Sri Lanka 2026 public/bank/mercantile/Poya calendar) is clear enough to distinguish it from the many other country siblings. However, it never explicitly positions itself against the sibling pair count_lk_working_days / add_lk_working_days, and the duplicated phrase 'Sri Lanka Sri Lanka' is a blemish.

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?

There is a 'Use this when...' opener, but the 'Do not use this when this is a combined official holiday-class calendar, not a universal private-employer closure rule' clause is malformed and does not name an alternative tool or a real exclusion condition. It does implicitly scope the tool to official holiday-class calendars rather than private-employer rules, which is useful. No guidance is given on choosing between this and its add_/count_ siblings.

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