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

Adds substantial behavior beyond annotations: the rotation advances and the next turn is scheduled, and the consent model ('draft'/'send'/'off', plus under-18 always drafting) is fully spelled out. This is exactly the kind of side-effect and authorization context annotations cannot 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-loads the action, then adds rotation and consent details. Dense and mostly earning its place, though the phrasing is slightly run-on ('The next time comes and the rotation moves on, as in the app').

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 present, return values need no explanation; the description covers the action, ID source, side effects, and consent resolution — everything an agent needs to invoke it correctly.

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 both choreId and household are already documented there, including the example value and the 'leave out when only one' rule. The description repeats the choreId provenance but adds no new syntax or format detail, so baseline 3 applies.

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?

Specific verb ('mark done') plus resource ('chore') with the actor scoped ('by the person'). It names the sibling read_chores as the source of the choreId, so an agent can immediately distinguish this write from the read tool.

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 when-condition: 'Only when the person says they did it.' It does not name an alternative action tool, but for this resource there is a clear read/write pairing with read_chores that is implied. Clear context, no explicit exclusions beyond the consent gate.

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