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

Annotations already establish readOnly, idempotent, non-destructive, and closed-world behavior, so the description is not obligated to restate safety. It still adds real value beyond them: the no-wake behavior (a meaningful trait in a fleet where many siblings require waking the car) and the caveat that cost is only present 'when Tesla reports it', which sets expectations about missing fields.

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, no redundancy, with the returned data front-loaded and the no-wake guarantee as a secondary clause. Every phrase carries information.

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 no output schema, six parameters at 50% coverage, and undefined pagination, the description leaves the agent guessing about result shape, default time window for 'recent', and page/page_size semantics. It covers purpose and the key behavioral caveat but is not complete for a six-parameter list tool.

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?

Six parameters exist and schema coverage is only 50%; start, end, and home_rate_usd_per_kwh are documented in the schema, but vin, page, and page_size are undocumented in both places. The description does not compensate — it says nothing about time-range filtering, pagination behavior, or how home_rate_usd_per_kwh triggers a cost estimate that isn't stored.

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?

Uses a specific verb and resource ('Returns recent charging sessions') and enumerates the session types (home, Supercharger, destination) plus the payload (kWh, cost). This clearly separates it from the sibling get_charging_status, which reads current state rather than history, although it never names that sibling explicitly.

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?

'Does not wake the car' implicitly tells the agent this is safe to call on an idle/asleep vehicle and needs no wake_vehicle preamble. However, there is no explicit statement of when to prefer this over get_charging_status or get_energy_usage, and no mention of default time window or required identifiers.

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