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

Annotations declare readOnly=false, destructive=false, idempotent=false, but the description adds real context beyond them: that draft content is replaced ('start over'), which brand/language/CSS/hero elements carry over, and the $0.001 per-call cost with 'nothing if it fails.' The failure-cost disclosure and carry-over list are exactly the behavioral detail annotations don't convey.

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 tight sentences with the reset behavior and carry-over front-loaded, followed by cost. No filler; each sentence contributes (action, carry-over semantics, pricing).

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?

No output schema exists, so the description must cover return/failure behavior, and it does state that failure costs nothing and (via schema) that a stale rev returns the current revision. Params are partly explained. Enough for an agent to call correctly, with only per-template detail deferred to the design guide.

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?

rev is fully documented in the schema, but template is an undescribed 6-value enum. The description compensates partially by pointing to the design guide for what each template looks like, adding meaning beyond the bare enum values, but it never explains rev or the carry-over relationship to the template choice. With 50% coverage, a 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?

The description uses a specific verb ('start the DRAFT over') and names the resource (a built-in template applied to the draft), which is concrete. It references the design guide, which routes the agent toward the sibling help_center_design_guide for template looks. Differentiation from save/update siblings is implied rather than explicit, keeping it at 4.

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 phrase 'start the DRAFT over from a built-in template' implies where this fits: resetting a draft to a template rather than editing it. It points to the design guide for choosing a template, but gives no explicit when-not guidance or named alternative (e.g. update_design vs save_article). Usage is workable but inferred.

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