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

Annotations establish the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), and the description adds genuinely new context: state is ephemeral, requires browser acknowledgement, and auto-clears after two minutes. These are behavioral traits not derivable from the structured fields. It omits what 'controlToken'/'expectedRevision' gate (likely auth and concurrency).

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 short sentences, front-loaded with the core action, then the constraints, then the auto-clear behavior. Every sentence adds information. Only mild redundancy is the slightly vague 'building indicator' phrasing.

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 and 0% parameter coverage across four required fields, the description leaves notable gaps: it does not explain the control token, revision check, or response/acknowledgement semantics beyond the word 'acknowledgement'. The ephemeral and auto-clear behaviors partially compensate, but the definition is not complete enough for a 4-parameter, fully-required tool.

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 description coverage is 0% on four required parameters, so the description carries the full burden and largely fails. 'Sets or clears' loosely maps to the status enum (working/finished) but says nothing about operationID, controlToken (an auth/control secret), or expectedRevision (a concurrency guard), leaving three parameters opaque.

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 ('sets or clears') and resource ('ephemeral building indicator'), and adds scope boundaries by saying it does not change workspace revision or publish drafts. The term 'building indicator' is somewhat idiosyncratic, but the negations separate it from the draft/publish siblings. It stops short of naming a direct alternative.

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?

There is no explicit 'use this when...' clause, but the exclusions ('does not change workspace revision or publish drafts') implicitly route the agent away from update_draft/publish_draft. The auto-clear note hints at the ephemeral-use case but does not state when an agent should invoke it.

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