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

Annotations only supply readOnlyHint=false and openWorldHint=true, so the description must carry most of the burden. It does usefully disclose the returned fields including the sensitive editToken and ownerUrl, but says nothing about authentication requirements, partial-failure behavior when an ASIN or query fails, or what 'curated' defaults get applied when no inputs are given.

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?

Three short sentences, front-loaded with the one-shot value proposition. The only redundancy is restating shopUrl/ownerUrl twice (once as the headline return, once in the full return list), which is minor.

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?

The tool has 10 parameters, zero required, and no output schema — meaning an agent could invoke it with an empty body and the description never explains what defaults apply, what the occasion parameter does when omitted, or why marketplace is effectively required despite not being marked so. It covers the happy path but leaves real invocation ambiguity.

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 30% across 10 parameters, so the description needs to compensate. It names three input families (ASINs, keywords, search queries) but is silent on locale, occasion, styleTags, budgetBand, relationship, and recipientName — several of which are self-evident enums, blunting but not removing the gap.

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 — create a curated wishlist and add items in one call — and the 'one call' framing distinguishes it from the create_wishlist + add_wishlist_item sibling pair. However, the description frames the tool exclusively as Mother's Day (Mors dag), while the schema's occasion enum also allows birthday, just-because, and other, so an agent may wrongly conclude the tool is Mothers-Day-only.

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?

'Preferred agent path: create a Mother's Day wishlist and add ASINs / keywords / search queries in one call' gives a clear selection signal against the multi-step create_wishlist path, though it never names the sibling explicitly or states when-not to use it (e.g., appending to an existing wishlist should use add_wishlist_item).

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