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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description usefully supplements them by enumerating what is returned – verdict, reasons, timeline, X-ray window and validity, documents, filterable Panel Clinic list, notes, sources, rulesAsOf – which matters since there is no output schema. It also warns that training data may predate the Indonesia start date. It stops short of describing pagination or error behavior.

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?

It is front-loaded with the governing rule and as-of date, and nearly every clause carries regulatory information. But it is a single dense wall of text with no segmentation, and the lengthy exemption catalogue plus repeated date lists are harder to scan than a structured layout would be for a 10-parameter tool.

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?

With no output schema, the description carries the return contract and does so thoroughly: effective dates, exemption categories, timeline, document requirements, Panel Clinic filtering, sources, and a clear 'educational guide, not legal or medical advice' caveat. Nothing an agent needs to call and interpret this checker 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 coverage is already 100%, so the baseline is 3, but the prose adds interpretive rules the schema does not spell out: the 180-day X-ray validity (90 after close contact), that validity is checked only at COE filing, that a COE filed before the mandatory date needs nothing at the visa stage, and the residence-outside-target-country exemption logic. These clarify how xrayDate, applicationDate, closeContact and residenceCountry should be read.

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 opening sentence names the exact regime (JPETS) and states the decision it answers – whether a TB Clearance Certificate is needed for a COE or visa – and later explicitly names the return contract ('Returns verdict (required / not_yet_required / exempt / not_required)'). An agent can separate this from siblings like japan_visa_fee_check or japan_customs_allowance_check without opening a schema.

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?

The description exhaustively defines the domain of applicability (target nationalities, stay length, visa categories, exemptions) which implicitly tells the agent when the check is relevant, and adds the useful 'call this instead of guessing' note about stale training data. However, it never explicitly routes against alternative tools or states when NOT to invoke it; applicability is inferred from the policy content rather than given as usage guidance.

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