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

Annotations only declare non-read-only, idempotent, non-destructive; the description adds far more — the reversible toggle semantics, the source of IDs, and a full consent model with draft vs send vs off and a hard under-18 rule. This is behavioral context the structured fields do not carry.

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?

Front-loaded with the action and toggle behavior before branching into the consent detail. Dense but every clause (done: false, itemIds source, consent states, under-18 rule) is load-bearing, though the consent sentence is long.

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 an output schema handling return values, annotations covering the safety profile, and the description covering invocation conditions, ID sourcing, and consent gating, an agent has everything needed to call this correctly or correctly decline.

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 done, itemIds, and household are already documented in the schema. The description reinforces done: false and itemIds' origin but adds no format or edge-case detail beyond that baseline, and never mentions the optional household parameter.

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 and resource (tick items off the household's shopping list) and explicitly covers the inverse operation via done: false. It also names where itemIds come from (read_shopping_list), so the agent can distinguish it from add_shopping_items and read_shopping_list at a glance.

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?

Gives an explicit usage condition — 'Only when the person says they bought them' — and names the sibling that supplies the required itemIds. It also spells out the consent gating (draft/send/off and the under-18 override), which tells the agent exactly when this may proceed.

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