List Recent Product Changes Across Stores

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description's 'List...' phrasing is consistent and adds no contradiction. The description adds the lookback-window scope and the returned field list, which is useful. However, it doesn't disclose pagination behavior despite the 'first' param limiting per-store results, nor clarify whether 'updated' means created or modified. With annotations covering the safety profile, a 3 is appropriate – the description adds some but not rich behavioral context.

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, efficient sentence with no redundant words. The primary action and scope ('List products updated during a selected lookback window across multiple stores') is front-loaded, with the field list appended at the end. Every word earns its place.

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 3-parameter tool with full schema coverage and read-only annotations, the description covers the basics: purpose, scope, and output fields. However, with no output schema and 21 overlapping sibling tools, it lacks (a) differentiation guidance and (b) clarification of 'updated' semantics and pagination. Given the ambiguity risk and sibling density, it falls short of fully complete.

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%; all three parameters (days, first, stores) are documented in the schema with descriptions. The description's phrases 'lookback window' (maps to days) and 'across multiple stores' (maps to stores) reinforce the parameter meanings but add nothing beyond the schema. Baseline 3 is correct when the schema carries the full semantic load.

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 ('List'), a specific resource ('products updated during a selected lookback window'), and states scope ('across multiple stores') along with included fields (status, inventory, vendor, product type). This is clear and distinct. It loses a point because it doesn't explicitly differentiate from similar siblings like shopify_search_products_many or shopify_get_product_everywhere.

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?

No guidance is given on when to use this tool versus the many overlapping siblings (shopify_search_products_many, shopify_get_product_everywhere, shopify_compare_catalog). The description never states 'use this when you need recent changes' or names an alternative for other cases. An agent reading the description alone cannot decide between this and the search/cross-store tools.

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