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

Discloses a non-obvious behavior: ambiguous or missing lists write nothing and return candidates, and the agent should report the returned details status exactly. Annotations already cover safety (readOnly=false, destructive=false), so this adds real context beyond them, though it doesn't mention auth or rate limits.

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 tight sentences, front-loaded with the core action, then the list-omission rule, the ambiguity behavior, and the follow-up instruction. Every sentence earns its place.

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?

Covers the main failure mode (ambiguous list) and the create_if_missing escape hatch, which is the key risk for a write tool with an openWorldHint. No output schema, but it tells the agent to report the returned details status. Slight gap on what the return actually contains.

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 all seven parameter descriptions are already documented. The description reinforces the list-omission and create_if_missing semantics, but at full coverage the 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 (capture one pick) and resource (a pick with the person's own note), distinguishing it from the bulk sibling add_items. Scope is clear but not explicitly contrasted with add_saved_item or save_item.

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 states when to omit `list` (deliberately use Inbox), how to handle ambiguity (writes nothing, returns candidates, ask the person), and when to set `create_if_missing`. This is a full when/when-not/alternative playbook.

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