Wake the car and re-read its state

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

The description discloses meaningful behavioral context beyond the annotations: it sends a wake request, consumes 12V battery and cellular time, and provides current state rather than cached parked state. This aligns with readOnlyHint=false and idempotentHint=true, with no contradiction.

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?

The description is three sentences with no filler: it front-loads the main action, then explains the limitation of passive reads, and finally gives cost and usage guidance. 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?

Given there are no parameters and an output schema exists, the description covers everything an agent needs: what the tool does, why it differs from passive reads, the cost, and when to invoke it. No critical information is missing.

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?

The tool has zero parameters and 100% schema coverage, so parameter semantics are trivially satisfied and the description does not need to compensate. The baseline for zero-parameter tools is 4.

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 states a specific action: ask the car to report its current state and re-read doors and climate. It also distinguishes itself from passive reads that only see parked data, making its purpose clear among many get_* sibling tools.

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 gives explicit guidance on when to use the tool ('when the user needs the state as of now') and when not to use it ('not routinely'). It contrasts with passive reads, but does not name a specific alternative sibling such as toyota_refresh_data, so the guidance is categorical rather than tool-specific.

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