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

Annotations already cover the safety profile (readOnly, idempotent, closed-world), so the bar is lower. The description still adds genuine non-structured context: raw_model_code is the smallest Build.MODEL among grouped devices, and url is null exactly when raw_model_code is null. It does not discuss pagination or scoping caveats, keeping it below 5.

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?

Core purpose and the when-to-use line are front-loaded in the first two sentences, then return details follow in a clearly separated block. The metric enumeration and URL explanation are somewhat long but each earns its place by clarifying output content.

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, annotations covering safety, and 100% parameter coverage, the description needs only to frame purpose and usage, which it does fully. The only minor gap is not contrasting with sibling aggregate tools by name.

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 parameters (brand, model) are documented with format examples in the schema itself. The description only restates 'brand+model' and the street-name vs. raw Build.MODEL matching is already in the schema, so it adds no meaning beyond structured data. 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?

States a specific verb (aggregate) and resource (battery metrics across all devices of a brand+model), and enumerates exactly which statistics (mean/median/p25/p75/min/max) and metrics are produced. This lets an agent distinguish it from device_summary (single device) and fleet_summary (whole fleet) without opening any schema.

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?

Explicitly states the two intended uses: 'characterize how a model behaves in the field' and 'compare a single device against its model average', the latter implicitly pointing at device_summary. It does not name alternatives outright or state when-not to use it (e.g. vs. top_models), so it stops short of a full 5.

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