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 bar is lower. The description still adds real value beyond them: the exact computation model, the pinned 2026-2027 coverage window, and the caveat that Bangkok-only, Islamic-bank and southern-branch conditions stay conditional and are not generalized.

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 labeled sections (What it computes / Inputs / Outputs / Formula / Docs) make it scannable and the use-case leads, but there is clear redundancy: complete JSON argument examples duplicate the schema's `examples`, and the Outputs list duplicates the existing output schema. The repeated "Thailand Thailand" phrasing also signals loose editing.

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, the description covers the trigger, the scope limits, the dataset window, the computation rule, the REST fallback and a docs link, which is more than enough to invoke it correctly. It is slightly over-complete in re-listing output fields that the output schema already provides.

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 the single `date` parameter is already documented as a Gregorian date within the pinned coverage window, so the baseline is 3. The description's "Inputs: date (date)" line and its JSON examples merely restate what the schema already contains.

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 (check a date against the Thai financial-institution working-day calendar) and pins the scope to the Bank of Thailand 2026-2027 dataset, which separates it from check_global_working_day and the many other country variants. However, the core purpose sentence is garbled ("deterministic Thailand Thailand financial institutions and specialized financial institutions result") and it never explicitly distinguishes itself from the add_th_working_days / count_th_working_days 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?

It gives an explicit use trigger ("Use this when you need a deterministic ... result") and a scope-based exclusion ("Do not use this when this is a Bank of Thailand financial-institution calendar, not a universal Thai employee, government, employer, exchange or payment-settlement calendar"), plus a directive to call it directly rather than answer from memory. The exclusion clause is grammatically broken and names no alternative tool, so routing is implied rather than clean.

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