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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint as false. The description adds valuable context: data source (MVA registration counts), breakdown by fuel category, monthly time series since 2020, and that the county file includes out-of-state counties flagged by 'in_maryland'. No contradictions with annotations.

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 a single, well-structured paragraph with no wasted words. It front-loads the core purpose, then provides examples and parameter details. Every sentence serves a clear function.

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?

The description adequately explains the output: counts split by fuel category, with a statewide total for context, and monthly data. It mentions two files (county and ZIP) and the in_maryland flag. Without an output schema, it gives a sufficient mental model for the agent. Minor gap: no mention of exact field names or pagination, but these are not critical for basic usage.

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?

Although schema description coverage is 100%, the description adds significant meaning: it explains that supplying 'zip' reads the ZIP-level file, that 'county' results include an 'in_maryland' flag, that 'group_by' can be 'county' or 'zip' with 'zip' implying group_by='zip', and that 'month' defaults to the latest published month starting from 2020/07. This enriches each parameter beyond the schema.

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 uses specific verbs ('measure', 'answers') and clearly identifies the resource (Maryland EV adoption from MVA registration counts). It explicitly distinguishes from the sibling tool md_dmv_vehicle_registrations, which covers the entire fleet across all fuel types. Example queries concretely illustrate the tool's scope.

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?

The description explicitly states when to use this tool vs. the sibling: 'For Maryland's whole registered fleet across every fuel type use md_dmv_vehicle_registrations.' It also provides multiple example questions and explains how to choose between county and ZIP-level data via the 'zip' or 'group_by' parameter.

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