Remember the dashboard confirmation choice

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

Beyond the idempotent/destructive annotations, the description reveals that the setting only affects dashboard care buttons while leaving model-requested care untouched. It implies persistence with 'Remember whether,' though it does not spell out that the choice is stored or how it interacts with an existing value.

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 short sentences deliver purpose, scope, and an exclusion without redundant phrasing. The main behavior is front-loaded and every clause 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?

For a low-complexity boolean setter with one required parameter, rich schema descriptions, and an output schema, the description covers all essential call context. It states what is affected, what is not, and the mutation's persistence is captured by the schema's 'from then on.'

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%, so the baseline applies. The description adds contextual scope ('dashboard buttons') but does not need to explain skipCareConfirmation or locale because the schema already documents both accurately.

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 names a specific resource (the AI Coach dashboard confirmation choice) and an action ('Remember whether...'), and immediately scopes it to 'dashboard use only.' This distinguishes it from sibling care-execution tools by stating it controls the dashboard's confirmation behavior, not care actions themselves.

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 explicitly says this is 'dashboard use only' and clarifies the when-not: 'care that the model asks for is always confirmed by the user.' Those statements tell an agent when this preference is relevant and prevent it from using the tool for model-initiated care.

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