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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, and the description adds real value on top: it confirms nothing is persisted, discloses the returned before/after text and version guard, and states the authorization precondition for channel edits. Missing only what happens on an unauthorized provider or a stale version.

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?

Four tight sentences, purpose front-loaded, followed by limits, preconditions, and return contents. No filler, though the word 'exact' adds little and the sentences are dense enough that the scope constraint could be broken out more clearly.

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 a read-only preview tool with five parameters, an output schema, and rich annotations, the description covers purpose, limits, preconditions, and non-persistence. The main residual gap is the expectedVersion input, which an agent must infer from the 'version guard' mention.

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?

With 0% schema description coverage across 5 parameters, the description carries the burden well: it explains the account vs channel scope, gives character limits (2,000 account, 500 channel — the 500 channel cap is not enforceable from the schema's maxLength of 2000), and states that channel edits need provider plus a workspace-scoped targetKey. Only expectedVersion is left unexplained, mentioned obliquely as an output 'version guard' rather than as an input.

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 a specific verb (previews) and resource (account or connected-channel editorial-guidance change), with scope qualifiers. It is clear enough to distinguish from read_profile_instructions, but it never explicitly contrasts itself with the closer sibling preview_profile_settings_change, leaving some ambiguity about which preview tool applies.

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?

'no change is saved' implies a preview-then-apply workflow, and the precondition that a channel edit requires an authorized provider and workspace-scoped targetKey gives useful context. However, no alternative or follow-up tool is named, and there is no explicit statement of when to prefer this over preview_profile_settings_change.

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