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

With no annotations, the description carries the whole burden and does so well: it discloses that event_class and availability are null for unclassified sites, that ended events come back with ended: true and must not be treated as upcoming, and that the server is read-only with prices/availability confirmed on the merchant's site. The inline A–E taxonomy explains the meaning of a returned field value that would otherwise be opaque.

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?

Return contents are front-loaded in the first sentence, followed by conditional behavior (Japan events, unclassified sites, ended events) and then lookup mechanics. The parenthetical A–E definitions are long but earn their place because no output schema documents those values; a little could be tightened, but nothing is padding.

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 read tool with no annotations and no output schema, the description is thorough about both the return shape and the semantic meaning of its fields. The remaining gap is failure behavior – what happens when the id or page URL matches nothing, or whether both keys may be passed together – which an agent may need in order to recover from a bad lookup.

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% and both optional parameters already describe themselves, including that page_url is 'an alternative to id' and that id comes from search_events or whats_on. The description restates those same facts rather than adding format constraints, mutual-exclusivity rules, or precedence when both are supplied, so it sits at the baseline when the schema does the work.

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 description opens with a specific verb and resource ('Return the full record for one event') and then enumerates exactly what that record contains: long description, booking links, stay link, page URLs per language. It is clearly a single-event detail fetch, distinct from the list-style siblings search_events and whats_on, which the description itself names as the source of the id.

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 lookup key precisely – 'by the id returned by search_events or whats_on, or by its canonical page URL' – which tells the agent how to get here from a sibling result. It does not spell out a when-not case (e.g. what to do when an id is unknown or an event is not found), so it falls short of full exclusions, but the intended flow is unambiguous.

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