shopify_delete_theme

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

The description discloses critical behaviors beyond annotations: this is a permanent deletion of a theme and all its files, the operation fails closed before dispatch until Spring can durably retain a recovery snapshot, and theme roles are protected. Annotations state destructiveHint=true, and the description expands on what gets destroyed and under what guard condition, which provides strong transparency for a destructive operation.

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 main narrative is front-loaded and efficient: the first sentence states what happens, the second warns about fail-closed behavior and protected themes. The Args list adds compact labels for each parameter. It is not bloated, though the paragraph lacks separation between user-facing usage guidance and implementation context.

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 that this is a destructive operation with annotations confirming destructiveness, the description appropriately emphasizes what can be deleted, what cannot, and the fail-closed safeguard. With an output schema present and no nested objects, it needn't explain return values. The only gap is that several parameters like idempotency_key, effect, and approval_ref may be required in practice even though schema marks them optional, and the description doesn't clarify prerequisites.

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 0%, so the description carries the full burden for parameter meaning. It explains theme_id and expected_preimage_sha256 meaningfully, but the remaining parameters (project_id, project_ref, connector_account_ref, idempotency_key, effect, approval_ref) get only terse labels like 'Authenticated Project UUID' and 'Exact project correlation reference.' That's enough to understand their role vaguely, but not enough to know how to obtain valid values. Baseline for low coverage is compensation; this partially compensates but leaves gaps.

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 opens with a clear verb+object: permanently delete a DEVELOPMENT theme and all its files. It also differentiates scope by explicitly stating what is immutable (UNPUBLISHED release candidates and MAIN themes). This distinguishes it from sibling tools like shopify_delete_theme_files or shopify_duplicate_theme.

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 description clearly states when the tool is applicable: only DEVELOPMENT themes, and explicitly states that UNPUBLISHED release candidates and MAIN themes are protected. It lacks an explicit pointer to alternative tools for those protected themes, but the exclusion is clear enough for an agent to know not to call this on non-development themes.

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