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

Annotations only declare readOnlyHint=true and destructiveHint=false; the description adds the substantive behavior an agent needs: the call is asynchronous, it returns a searchKey plus sessionId/status/totalHotels, and no authentication is required. That is real context beyond the annotation surface rather than restatement.

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?

Purpose, return values, requirements, and downstream chaining are front-loaded in that order, and the 'collect missing details instead of guessing' sentence earns its place. There is minor overlap with the schema's required list and format notes (dates, ISO codes, adults range), which keeps it from a 5.

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-value burden and does so explicitly (searchKey, sessionId, status, totalHotels). For a 9-parameter async search tool it covers inputs, side effects, auth, and the follow-up contract, leaving nothing essential unstated.

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 baseline is 3, but the description adds the cross-parameter constraint that the agent must supply EITHER regionId OR latitude+longitude, plus the hint that currency is 'strongly recommended' even though optional. It restates some schema-level facts (YYYY-MM-DD, 1-4 adults, 2-letter ISO) which limits it to a 4.

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 clause names a specific verb and resource ('Starts an asynchronous hotel-availability search') and immediately names the artifact produced ('searchKey'). It also distinguishes itself from siblings by stating the returned key is consumed by get_search_results, get_hotel_rooms, and prepare_booking, so an agent can place it in the workflow without opening other schemas.

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 clear pre-call guidance (collect check-in date, derive endDate from nights, rooms/adults, nationality rather than guessing) and explicit post-call routing (poll get_search_results, reuse the same searchKey downstream). It also frames the regionId vs latitude/longitude choice, though it does not explicitly say when NOT to use this tool versus search_location.

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