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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered; the description adds genuinely new behavioral context — data is as published on the website and may change, hours vary by season, and reservation: null signals the site offers no reservation. It also explicitly disclaims any booking capability, which prevents an agent from assuming the tool can act.

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?

The content is dense and mostly earns its place, but the opening is a verbless noun phrase followed by fragmented clauses ('access: hotel_guests, other_guests with their condition...') that read like field notes rather than prose. The trailing 'API v3.' is noise, and the access/min_age detail would be better structured than run together mid-paragraph.

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 burden of explaining returns, and it does so by naming access_for_hotel, the access categories, min_age with age_note, and reservation with phones and URL. Combined with the seasonality caveat and out-of-scope note, an agent has enough to call and interpret this correctly; only the behavior with no filters applied is left implicit.

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% with all three parameters enum-documented, so the baseline of 3 applies. The description adds modest meaning for 'hotel' by framing it as an access filter rather than a location filter, but it says nothing extra about 'lang' or 'type' beyond the schema's own enum descriptions.

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 enumerates exactly what the tool returns — restaurants, bars, cafés, spa, room service and beach service across the five Corissia hotels — including hours, prices, access and reservation links, which clearly separates it from siblings like get_venue and get_menu. It never uses an explicit verb such as 'list' or 'returns', leading with a bare noun phrase, and it does not name the sibling tools it is distinguished from.

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 concrete usage context for the optional hotel filter ('the venues its guests may use') and clear exclusions: the connector does not reserve tables or treatments, and what a board includes 'is not part of this answer', which implicitly routes those needs elsewhere. It stops short of naming alternatives such as get_venue for a single venue's detail or get_menu for menu contents.

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