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

Annotations already flag destructiveHint=true and idempotentHint=true, and the description goes further by naming exactly what is destroyed ('Unpublished draft edits are replaced') and clarifying the blast radius ('does NOT go live until you publish it'). It also discloses the optimistic-lock refusal behavior and the 404 version_not_found error, so an agent knows both the side effects and the failure modes before calling.

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?

Front-loaded with the core action and the critical 'not live until publish' caveat before any argument detail, and the Args/Returns/Errors block is easy to scan. Minor padding remains in the parenthetical comparison to the Template Editor's one-click revert and the 'so the customer can review it first' aside.

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 destructive, non-read-only mutation with no output schema, the description supplies the return value ('the draft status') and the documented error code, plus the draft-replacement and non-publishing semantics. Nothing an agent needs in order to invoke this safely 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 description coverage is 100%, so the schema already documents all three parameters in depth, including the etag lock semantics and the agent_key credential handling. The description's Args block largely restates that, adding only a pointer to helpcenter_list_template_versions for version_id, which the schema also mentions. Baseline 3 is appropriate.

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 precise verb and target: load an earlier published design into the DRAFT, replacing the draft's content. It also distinguishes itself from the publish path ('It does NOT go live until you publish it'), so an agent can tell it apart from helpcenter_publish_template and helpcenter_restore_article_version without opening any schema.

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?

Gives concrete intent triggers — 'to undo a change, or bring back a previous look' — and points at helpcenter_list_template_versions as the source of the version_id, which is the necessary prerequisite. It stops short of naming the adjacent alternatives (e.g. helpcenter_discard_template_changes for throwing away a draft versus restoring a published version), so the exclusion set is inferred rather than stated.

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