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

Annotations declare readOnlyHint=false and openWorldHint=true, so the write/open-world nature is already covered. The description adds useful context beyond that: the tool performs searches and creates wishes in one call and returns shopUrl (share link) + ownerUrl, which matters since no output schema exists. It does not disclose side-effect details an agent would want for a mutation tool — partial-failure behavior if some ASINs/queries fail to resolve, duplicate-wishlist risk, or rate/latency implications of running searches inline.

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 core action and the preferred-usage steer, followed by return values. 'OpenAPI: agentCreateAndFill' is a cheap but useful spec pointer rather than padding. Little waste overall.

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?

It correctly compensates for the absent output schema by naming the two returned URLs, and it conveys the create-plus-fill scope. For a 10-parameter open-world mutation tool it is still thin: no statement of the marketplace requirement, auth expectations, locale/marketplace interaction, or what a partially successful fill looks like.

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?

With 30% schema description coverage across 10 params, the description does add meaning where the schema is silent: 'add ASINs / keywords / search queries' maps to itemAsins, itemKeywords, and itemQueries, clarifying that each query is executed and its result added. However seven params (occasion, budgetBand, giftCategories, hostName, dietaryNotes, locale, marketplace) get no mention, and the description omits that marketplace is effectively REQUIRED despite the schema reporting zero required fields.

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+resource ('create a curated new mum / postpartum gift wishlist') and adds the composite behavior ('and fill'), plus what it returns. The line 'Preferred agent path: create a wishlist and add ASINs / keywords / search queries in one call' implicitly separates it from create_wishlist + add_wishlist_item, though it never names those siblings directly.

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' is a real usage steer: it tells the agent to prefer this one-shot tool over the multi-step alternative. But it gives no explicit when-not-to-use, no named alternatives (create_wishlist, add_wishlist_item exist as siblings), and no prerequisites such as auth or required marketplace, leaving selection partly to inference.

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