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

Annotations already declare readOnly=false, openWorld=true, idempotent=false, destructive=false. The description adds two pieces of value beyond them: the 50-item cap and the all-or-nothing write semantics ('list must resolve to exactly one ... or nothing is written'), which tells the agent a bad list fails the whole batch. It does not mention the idempotency_key reuse pattern or describe partial-failure/response behavior.

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 waste, front-loaded with the capacity and ordering guarantee before the routing distinction from add_item. Every clause carries operational information.

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 no output schema, the combination of annotations (safety, idempotency hints) plus the description's failure semantics is nearly sufficient. The remaining gap is what a successful call returns and how the idempotency_key should be used after a timeout — the latter is covered in the schema, so the shortfall is minor.

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 100% and the nested item fields (url/note/title/author) are richly documented, so the schema carries the load. The description only adds ordering and the strict resolution requirement for `list`, which the property description ('exact slug, handle/slug, or id') already covers. Baseline 3 is appropriate.

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 (Add), resource (picks), batch size (up to 50), target (one list), and ordering guarantee — all in the first clause. It then names the sibling add_item and the exact behavioral difference, so an agent can separate the two without opening either schema.

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?

Explicitly contrasts with add_item and gives the decisive selection condition: this tool never falls back to the Inbox, so a resolvable `list` is mandatory. Clear context and a named alternative, but it stops short of stating when singular add_item is preferable (e.g. one-off adds) or how it relates to stage_picks/confirm_items in the bulk-import flow.

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