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

Adds substantial behavior beyond the annotations: status is re-verified live against Airwallex when not already confirmed paid, results are tenant-scoped to the caller's own account, and a specific token with the 'bookings' scope is required. These are exactly the freshness, authorization, and data-isolation facts an agent needs and that readOnlyHint does not convey.

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?

Three tight sentences, front-loaded with the action and key, followed by the freshness guarantee and the auth/scope constraints. No filler or restated name.

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 single-parameter read with no output schema and annotations already covering the safety profile, the description covers the remaining unknowns: freshness of the result, tenant isolation, and the required credential/scope. Nothing an agent needs 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%, and the pnr description already maps to its source ('returned by bookStay'). The tool description adds only 'by PNR', so it does not meaningfully extend the schema; baseline 3 is appropriate.

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 and resource ('Check a Stay booking's real payment status by PNR') and adds a scoping qualifier ('real payment status') that distinguishes it from sibling status-like tools such as getPurchaseStatus and listMyBookings. An agent can identify the target record type and the required key without opening the 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?

Gives clear framing for use ('never trust a client-supplied claim of success', implying it should be called to verify after booking) but does not explicitly name an alternative tool or a when-not condition. Context is clear without exclusions, which caps this at 4.

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