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

With no annotations, the description carries the full behavioral burden and does well: it discloses that a month whose as_of precedes month-end is PARTIAL, that brand-only queries elsewhere disclose truncation in a `note` field, and that the kind default differs from the sibling's. It does not cover permissions, rate limits, or the shape of returned rows, so it falls short of full disclosure.

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 core resource and dimensions are front-loaded, but the text is a single dense paragraph with no structural breaks and the final sentence about brand totals is convoluted and partly redundant with the earlier 'Market-level ONLY' caveat. It is informative but could be tightened without losing meaning.

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, the description must carry return semantics, and it does explain what each dimension yields plus the `note` truncation field and the as_of partiality rule. It stops short of describing the actual output structure per dimension, leaving some uncertainty about returned fields.

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 coverage is 100% and enum descriptions are terse ('Which slice to return'), but the description genuinely expands each dimension value with real semantics: imports is by toldsyn date with counts/share/top makes, monthly_totals covers the last 12 months including leasing series, and brands is limited to the top 20. It also explains kind=all vs kind=Personbil beyond the schema's bare 'Default: all'.

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 (Danish new-vehicle registration statistics from bildata.io weekly DMR data) and enumerates the exact dimensions returned (fuel_type, brands, evs, imports, monthly_totals, country_of_origin). It explicitly distinguishes itself from get_model_stats for per-model queries, so an agent can separate it from siblings without opening a 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?

It states both when to use this tool (market-level questions) and when not to (per-model breakdowns, brand totals for brands outside the top 20), and names the correct alternative (get_model_stats) for both exclusions. It even explains why the sibling's output cannot be summed to reproduce this tool's brand totals, which removes a real misuse path.

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