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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavior: results may be partial mid-search and a status field flips to 'completed' once every source has responded — essential for an agent deciding whether to re-poll.

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 sentences, no filler, and the highest-value information (what it returns and the session linkage) is front-loaded. The partial-results caveat follows immediately behind it.

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?

An output schema exists, so return-value documentation is not required; the description nonetheless sketches the shape. The async/polling semantics, the prerequisite tool, and the downstream consumers are all covered, leaving nothing an agent needs to call this correctly.

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% across all 9 parameters, so the schema already documents sessionId provenance, pagination, limit, and the filter overrides. The description adds essentially no parameter-level detail beyond what the schema states, so the baseline 3 applies.

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 ('Returns the current results of a hotel search session') and anchors it to the sibling that creates the session (search_hotels_live). It even enumerates the payload shape — hotels with per-source prices plus OpenTravel direct listings — so an agent can distinguish it from search_hotels_live without opening either 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?

Clearly implies the workflow: call after search_hotels_live, poll while results are partial, expect status 'completed' when all sources answer. It also names the downstream consumers (get_hotel_detail, get_hotel_info) via propertyId. It doesn't state explicit exclusions or a polling interval/backoff, so it falls short of a full 5.

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