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

Annotations already declare non-readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds a real behavioral fact beyond that: consuming/viewing a page via rendering or polling is not a substitute for an explicit ack — which is exactly the distinction an agent needs to avoid wrongly assuming the change was consumed.

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?

Two sentences, zero filler, and the critical constraint (rendering/polling is not an ack) is placed second where it reads as a caveat rather than being buried.

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?

An output schema exists, so return values need not be explained. However, for a write tool the description does not say what acknowledgment actually does downstream (advance a cursor, mark the page consumed) or whether the token is single-use — context that the idempotentHint alone does not settle.

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 67%; workspaceId and why are documented in the schema (the why field even notes it is accepted but not recorded). deliveryToken has no description in either place, and the description only hints at it via 'one delivered ... page' without stating that it identifies a single page or where it is obtained.

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?

States a specific verb and resource: 'acknowledge one delivered workspace change page'. That clearly separates it from the read-oriented sibling workspace_changes, though it never names that sibling 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?

'Explicitly acknowledge' plus 'Rendering or polling does not acknowledge it' gives an implicit precondition, but the agent is not told where a deliveryToken comes from or which sibling produces the change page to acknowledge.

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