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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description still adds substantive behavior: it returns fit evidence, limitations, official routes and expiring selection tokens, and it warns that results are conditional rather than confirmed availability. The expiring-token disclosure is exactly the kind of downstream consequence an agent cannot infer from structured fields.

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?

Front-loaded with the capability and the no-ID affordance, then layered constraints, return contents, coverage caveat, and interpretation warning in five dense sentences. Nothing is repeated and no sentence is filler.

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 an 8-parameter nested tool with no output schema, the description does the important work: it describes what comes back and how to interpret conditional results. The main remaining gap is workflow continuity — it never says the expiring selection token is what feeds prepare_discovered_stay, which the agent needs to close the loop.

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 0% across 8 parameters with nested objects, so the description must carry the semantic load and largely does not. 'Destination and traveler fit' loosely gestures at destination and guest_count, and 'budget-matching' hints at the budget object, but nothing explains limit, language, preferences, required_constraints, or the JPY-only currency constraint.

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 — find eligible owner-approved customer property records — plus the key affordance: it works 'without knowing a property name or ID.' That framing cleanly separates it from get_customer_property and search_availability, so an agent can pick it 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?

Gives clear when-to-use context (destination/traveler-fit discovery with no name or ID) and explicit exclusions (no live availability, no price, coverage limited to this approved catalog). It stops short of naming the sibling to call instead — e.g. search_availability for live rates or prepare_discovered_stay to act on a token — so routing is implied rather than stated.

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