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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds only two behavioral facts beyond that: installation_id provenance and that getRoomBookingIntegrationConnectUrl returns a URL meant to be handed to the owner. It says nothing about pagination on the list operations, result shapes, or any auth needed to reach an installation.

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 structured bullet list is well front-loaded and scannable, but the preceding single-sentence inventory of the domain ('its summary, billing state and settings; its calendars and what each device showing one has rendered...') is a hard-to-parse run-on that largely previews the same resources the bullets then enumerate. Trimming or merging that opener would sharpen the definition without losing content.

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 an 11-operation dispatcher with no output schema, the description covers the essential routing information: every action, its parameters, parameter location, and where installation_id originates. It is missing return-value/pagination expectations for the list actions and any note on how failures per action surface, which keeps it from being fully self-sufficient.

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?

The schema's params object is opaque ('path, query and body parameters by name'), so the description is the only place that enumerates which parameters each action takes and whether they are path or query (e.g. id path, from/to/status query). That is real added meaning, though it stops at names and locations — no formats, types, or valid status values are given, and the per-action mapping only works if the agent reads the bullet for the chosen action.

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 bulleted action list gives a specific verb+resource for each of the 11 operations (getRoomBooking, listRoomBookings, getRoomBookingBilling, etc.), so the agent can tell what each sub-operation does. The opening sentence is a dense noun-phrase run-on that never states a clear 'read X' verb for the tool as a whole, and the sibling AccountRoomBookingWriteTool is never named as the mutating counterpart.

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?

The per-action lines effectively route the agent to the right sub-operation (bookings vs calendars vs screens vs integrations), and it explicitly states 'The installation_id comes from listAppInstallations', giving a prerequisite/where-to-get-input instruction. However, there is no explicit when-not-to-use guidance and no direct reference to AccountRoomBookingWriteTool for mutations beyond the naming convention.

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