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

Annotations cover the safety profile (readOnly, non-destructive, non-open-world), but the description adds substantial behavior: the registry is small and growing, the no-match fallback path, that hits optionally carry the cheapest offer plus booking_url only when stay params are supplied, and that other_hotels is sourced from an agent-readiness index with no rates/links. This is exactly the context annotations cannot 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?

Purpose and scoping are front-loaded in the first sentence, and each subsequent sentence carries routing or fallback information. It is a single dense paragraph with some long nested clauses (the checkin/nights/guests offer sentence), which slightly taxes readability but wastes nothing.

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 search tool with two result sets (registry hits and other_hotels) and no output schema, the description covers what each result carries (hotel id, cheapest offer, booking_url, level, site) and the fallback behavior. Nothing an agent needs to call it correctly or interpret its results 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 baseline is 3. The description goes further by explaining that 'area' means where the traveller wants to stay (not their current location), giving bilingual examples, and defining the min_level scale (0 invisible to 4 transactable) and what it filters. It does not add syntax beyond the schema for checkin/nights/guests, so it stops short of a 5.

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+resource+scope: searching VibeBooking's registry of independent hotels and inns in Japan by destination area, with concrete area examples. It explicitly names siblings (get_hotel, get_rates, resolve_hotel) and the role each plays, so an agent can distinguish it without opening 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?

Explicit when-to-use and when-not-to-use: if the registry has no match, the agent is told to fall back to its own web search and then call resolve_hotel per domain. It also states when to route hits onward to get_hotel or get_rates, and clarifies that other_hotels are outside VibeBooking and carry no rates or booking links.

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