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

Annotations already declare readOnly/idempotent/openWorld, and the description still adds material behavior: results are ordered newest year first, some years are DfT estimates with each row flagging that, both directions are aggregated, the vehicle-class breakdown is enumerated, and it costs 1 credit. These are exactly the caveats an agent needs to interpret output and set expectations, none of which appear in the 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 core definition and unit of measurement are front-loaded in the first clause, followed by example questions and caveats in a single dense paragraph. Every clause carries information, though the parenthetical cost note and the long vehicle-class enumeration make it slightly heavier than necessary.

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 steps in to describe the returned shape (per-vehicle-class daily flows, one row per year, newest first) and the estimation caveat, which is the critical completeness gap it must fill. Only the count-point source hint and pagination/limit behavior are left to the schema, so it is close to complete for this tool's complexity.

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%, so all three parameters (year, years, count_point_id) are already documented with types and defaults, establishing the baseline of 3. The description reinforces semantics ('newest year first', default most recent years) but adds no new syntax, ranges, or id-format guidance beyond what the schema states.

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 verb and resource ('Gives average annual daily flow (AADF) at one DfT count point') and immediately defines the metric (average vehicles per day over a year, both directions, split by vehicle class). The scope qualifier 'at one DfT count point' implicitly distinguishes it from region/local-authority aggregates and hourly-count siblings, so an agent can select it without opening other schemas.

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 concrete usage framing ('Answers "how many cars pass this site a day" and "is traffic on this road rising"') and names real use cases (shop, billboard, EV charger, planning work), plus an exclusion: 'it does not cover live traffic or congestion'. That exclusion steers agents away from hourly/live siblings without naming them explicitly, which is the only gap.

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