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

The annotations already indicate a non-read-only, open-world, non-destructive, non-idempotent operation. The description adds important behavioral context beyond that: the call is ordered, capped at 50, and is all-or-nothing when `list` does not resolve exactly once.

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, front-loaded with the core action and limits. Every sentence adds distinct information: batch scope, ordering, and failure/fallback behavior.

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 mutation tool with rich schema descriptions and annotations but no output schema, the description covers the critical call semantics: batching, ordering, max size, and all-or-nothing resolution. It leaves retry behavior to the schema's `idempotency_key`, which is reasonable given the schema coverage.

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 schema already documents all three parameters thoroughly. The description still adds semantic value by emphasizing that `list` must resolve to exactly one of the curator's lists or nothing is written, a constraint not fully captured in the schema's `list` description.

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 states a specific verb and resource (add picks), the batch limit (up to 50), ordering, and the single-list scope. It also explicitly distinguishes this tool from add_item by noting that add_items never falls back to the Inbox.

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?

It names the sibling alternative add_item and clarifies a key behavioral difference: add_items does not fall back to the Inbox and requires `list` to resolve to exactly one curator list. This gives clear selection guidance, though it does not fully spell out the inverse case for using add_item instead.

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