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

Without needing annotations it discloses credential semantics (token IS the credential; wrong token returns not_found so ids can't be probed), cancel idempotency, reschedule atomicity ('an error means nothing changed'), and it never skips authorization, only moves it into the resource. The one mismatch is that annotations declare idempotentHint=false while the description says action:cancel is idempotent — defensible at tool level since reschedule mutates, but it is a nuance the reader must reconcile.

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?

Almost every sentence carries operational payload, but it is delivered as a dense wall of prose with rhetorical asides ('ghosts', 'burns members' time', 'emails a human to be removed') and the purpose is not front-loaded. The size is larger than the task requires; a structured list of auth model / per-action behavior / errors would read far faster.

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With no output schema, the description carries return-shape duty and does so: it documents booking/superseded/cancel_token fields, the NEW-id-after-reschedule rule, meet_link status transitions, and the full error_kind set (not_found, slot_taken, outside_window, too_soon, rate_limited, validation, transient). Nothing an agent needs to call or interpret this tool 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 already 100%, so the baseline is 3; the description earns a step above by explaining parameter interplay the schema cannot — that start must come from a fresh availability call because responses go stale, that idempotency_key is minted server-side if omitted but should be reused on retry, and that reason is member-visible. It still largely restates the arg list.

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 title and body state a specific verb set (read/cancel/reschedule) on a specific resource (one booking) keyed by cancel_token, and the actions are enumerated explicitly. It is distinguishable from siblings and even names ic_scheduling_get_availability as the source of a reschedule slot. Marks off only because the body opens with rhetorical framing ('The way OUT of a booking...') instead of the operational statement the title already gives.

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' rules throughout: confirm cancel and reschedule with your human first, reschedule needs a start from a FRESH availability call, poll meet_link no faster than every 2s for at most 90s, reuse idempotency_key on retry. It also states which action is safe/repeatable versus which mutates a real calendar.

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