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

Annotations provide readOnlyHint=false, openWorldHint=true, idempotentHint=true, destructiveHint=false, but the description adds substantial context beyond them: the side effect that a new email creates an agent, the return shape (items found and how many other agents want each), the server-failure behavior, and the boundary that btw doesn't buy from Amazon. These are exactly the behavioral disclosures annotations can't capture.

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?

The core action is front-loaded in the first sentence, and the description is dense with actionable information. However, the final sentence ('The link is how we know what you want; the group price comes from the brand.') is partly redundant with the purpose statement and adds only marginal value, keeping this from a 5.

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?

With no output schema, the description correctly explains return values, failure modes, and side effects, giving the agent a complete decision tree for the fallback path. The one gap is that url and asins are both optional in the schema and the description only implies they are alternatives, never stating exclusivity or what happens when both are provided.

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 coverage is 100%, so the baseline is 3; the description adds meaning on top by explaining the fallback relationship between `url` and `asins` (pass ASINs only if the server can't read the list), the email side effect (a new email gets an agent), and that the URL is the signal for what the human wants. This goes beyond restating the schema 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?

The first sentence states a specific verb and resource: 'Read a public wishlist and add every item to your human's btw agent.' It names the supported sources (Amazon, Steam) and explicitly differentiates from the sibling `want` by describing it as the per-product fallback ('call want once per product link'), so an agent can tell this bulk-import tool apart from the single-item tools.

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 gives an explicit conditional routing path: if the server can't read the list, the agent should open it itself and pass ASINs, or call `want` per product link. It also notes the new-email side effect. This is clear context with named alternatives, though it doesn't state a primary when-to-use/when-not-to-use rule beyond the implied 'bulk wishlist import' case.

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