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

The annotations declare idempotentHint=false, yet the description asserts 'Retry-safe: a repeat call with the same idempotency_key returns the original result' — since idempotency_key is a required argument, repeating the call with identical arguments is claimed to have no additional effect, which directly contradicts idempotentHint=false. Per the scoring rule, a description that contradicts annotations scores 1. The other hints (readOnly=false, destructive=false, openWorld=true) are consistent, but the idempotency conflict is material for an agent deciding whether a retry is safe.

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?

Two sentences, zero filler, with the core action front-loaded and the retry behavior placed second. Every sentence contributes something an agent would want before invoking the tool.

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?

This is a mutating, open-world sync with six parameters, 50% schema coverage, and no output schema. The description covers the core mechanism but omits what an agent still needs: whether workspace_id/brand_id are required for this write, whether products absent from the store's catalog are removed or left stale, and what permissions or connection state are prerequisites. Given the mutation and missing structured coverage, the description under-delivers.

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 only 50%, so the description must carry weight; it does add real meaning for idempotency_key (dedup/retry semantics that the schema's pattern and example do not convey), and 'a connected store' implies id is the store identifier. However, it says nothing about body, query, brand_id, or workspace_id — notably whether a workspace must be supplied for this write.

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?

States a specific verb and resource ('Re-sync a connected store's product catalog') and then explains the mechanism ('fetches the store's products and upserts them into the workspace'). This clearly distinguishes it from its nearest siblings aidelly_list_ecommerce_products (read) and aidelly_disconnect_ecommerce_store (teardown) without needing to name them.

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 word 'Re-sync' implies the situation (refresh a catalog already connected), and the retry sentence gives a usage condition for repeat calls. But there is no explicit when-to-use/when-not, no statement of prerequisites (e.g., that a store must be connected first), and no pointer to sibling alternatives.

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