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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: what the response contains (busy spans and blackout closures), how fullness is computed for shared spaces via seatsTaken vs seats, and a prompt-injection warning that person-typed text arrives under an `untrusted` key. Return shape and pagination/timezone handling remain undisclosed.

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, front-loaded with the returned data before the seatsTaken interpretation and the safety warning. Each sentence earns its place, though the phrasing 'the space has seats in all' is slightly awkward and the seatsTaken rule could be tighter.

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 must carry the return contract, and it does the important parts: busy slots, blackout closures, seatsTaken on shared spaces, and the untrusted-text convention. For a 4-parameter read tool this is close to sufficient; only timestamp formatting and whether free gaps are implicitly the complement are left unstated.

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 50%: roomId and workspaceId are documented in the schema, while fromUtc and toUtc carry no description there. The description partly compensates by capping the interval at 31 days, which meaningfully constrains those two undocumented date-time parameters, but it says nothing about UTC assumptions or inclusive/exclusive endpoints.

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 names the exact resource and scope: busy/booked time slots plus blackout closures for a single space, bounded to a window of at most 31 days. It is a noun phrase rather than a verb, but an agent can immediately tell this is the availability read, distinct from siblings like find_free_rooms or list_my_reservations, though it never names the alternative explicitly.

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?

Usage is only implied: the 31-day maximum window is an invocation constraint that stops an agent from requesting a huge range, and the seatsTaken explanation tells it how to interpret results for shared spaces. There is no statement of when to prefer this over find_free_rooms (which presumably returns free gaps) and no mention of prerequisites such as needing roomId from list_rooms.

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