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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description adds substantial context beyond them: anonymous ToC queries work without user_key, while booking/order/cancel/payment operations require a client-configured user_key. It also discloses the error taxonomy and retry policy, which annotations cannot express.

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 tool's own behavior is front-loaded and the key sequencing rule appears early. The auth paragraph spends several clauses on booking/order/payment operations that this read-only tool never performs, which is slightly off-target but still fast to scan.

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 an output schema present, return values need no explanation, and the description covers the remaining agent-critical points: required sequencing with search_hotels, the no-fabricated-IDs constraint, auth requirements, and how to handle failures. Nothing essential to invoking 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 coverage is 100%, so the schema already documents both parameters in detail (non-blank keyword, user_key sourcing and when it is required). The description restates the user_key optionality for ToC lookups, which is marginally useful but largely duplicates the schema, so it lands at the baseline 3.

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 first sentence gives a specific verb (resolve) plus the exact resource types (region, POI, landmark, mall, hotel name) and the output form (TourMind regions, hotels, coordinates). The follow-up sentence explicitly separates this from search_hotels by stating this tool resolves names first and search_hotels consumes the resulting IDs/coordinates.

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 states the intended sequence ('use this tool first to resolve the location/hotel name, then search hotels with the returned ID or coordinates'), forbids fabricating IDs, and gives explicit failure-handling guidance (distinguish parameter/auth errors from transient upstream failures; retry only transient ones a limited number of times).

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