Audit Shopify Catalog Health

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

Annotations already disclose the operational profile: readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description contributes useful scoping — 'recent products' and 'selected stores' — plus the concrete list of attributes checked. It doesn't disclose potential nuances like API rate limiting across multiple stores, failure behavior on one bad store alias, or result shape, but for a safe read-only audit the description plus annotations are adequate.

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?

A single, well-constructed sentence with zero wasted words. The key verb 'Audit' is front-loaded, and the list of six audit dimensions is compact yet exhaustive. Every element earns its place — no filler, no redundancy.

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, idempotent audit tool with 100% schema coverage and descriptive annotations, the definition is thorough: it names the exact checks, the scoping via 'recent' and 'selected stores,' and the input shape. The only minor omission is the lack of any description of the output/report format, but since no output schema exists and the audit criteria are explicit, an agent has enough to call it correctly.

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% — both `first` ('Maximum recently updated products scanned per store.') and `stores` ('One to ten configured store aliases') are documented inline. The description's 'recent products' loosely maps to the `first` parameter and 'selected stores' maps to `stores`, but adds no new syntax or format detail beyond what the schema already provides. Per the baseline rule (coverage >80%), score 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 names a specific verb ('Audit'), a precise resource ('recent products across selected stores'), and an exhaustive list of audit dimensions (missing vendor, product type, SEO fields, featured media, media alt text, active products without inventory). Despite sharing the 'catalog' them with siblings like shopify_catalog_gap_report and shopify_compare_catalog, the distinctive multi-attribute check list makes its purpose unmistakable and non-overlapping.

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 implies its usage context — auditing catalog hygiene across selected stores — through the phrase 'across selected stores' and the specific checks performed. However, it never names alternatives or when NOT to use it. Given the crowded sibling space (shopify_catalog_gap_report, shopify_compare_catalog, shopify_recent_product_changes), explicit exclusion guidance would have earned a higher score; as-is, the agent must infer fit from the audit criteria.

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