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

Annotations already include destructiveHint=true and idempotentHint=false. The description goes beyond by detailing the blast radius ('swaps the ENTIRE website'), the need for double confirmation (expected_updated_at lock, theme name typed back), and the approval queue behavior. It also discloses the 'no standing grant' policy. No contradictions.

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?

The description is well-structured with a clear lead sentence defining the action, followed by risk warning, then routing details. It is slightly verbose with the outbound-tier note, but each sentence adds critical safety information. Front-loads the core purpose and risk, making it efficient.

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?

Given the high risk of this action, the description is thorough: it covers approval requirements, confirmation parameters, and the irreversible nature of the swap. No output schema exists, but the description doesn't need to explain return values; it focuses on what the agent must know to execute safely. It also distinguishes from sibling publish tools.

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 100%, so baseline is 3. The description adds value by clarifying the purpose of confirmation parameters: expected_updated_at is a lock to prevent race conditions, and confirm_theme_name must be typed back exactly to prevent mistakes. It also emphasizes that theme_id must currently be unpublished, which is a semantic constraint not in the schema.

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 clearly states the verb 'Publish' and the specific resource (Shopify theme) and outcome (becomes LIVE storefront). It distinguishes itself from sibling tools like publish_shopify_page and publish_shopify_product by emphasizing it swaps the entire website.

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 states when to use: only when the operator approves a full storefront go-live. It also explains the approval workflow, including that every call requires manager approval and the approval card is the yes. It contrasts with routing instructions and outbound-tier notes, providing clear conditions and alternative actions.

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