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

Annotations already cover safety (readOnly, idempotent, non-destructive, open world), and the description adds genuinely new behavior: partial-name matching with concrete examples, dual accepted input formats, coverage that includes retired councils, and a 1-credit cost. The one unaddressed trait is ambiguity handling — 'Kingston' plausibly resolves to several councils, and the description does not say whether the result is one match, a list, or an error.

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?

Front-loaded with the return value, then accepted inputs, then call ordering, then scope limits — the four things an agent needs, in priority order. Every clause earns its place, including the short parenthetical credit cost, and there is no filler or repetition of the title.

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 correctly states what comes back (id, ONS code, region), so the agent knows what it will receive. Given the tool is a simple single-param lookup with full annotation coverage, the only meaningful omission is what a multi-match or zero-match partial name returns.

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 the single parameter is already documented as 'council name or part of it, or an ONS code like E08000035'. The description reinforces this with additional worked examples ('Leeds', 'Bristol', 'Kingston') and confirms partial matching works, but adds no format rules or disambiguation beyond the schema. Baseline 3 is appropriate when the schema carries the parameter burden.

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 (finds) and precise resources (DfT local authority id, ONS code, region) scoped to councils. It also distinguishes itself from a near-miss sibling by saying explicitly 'it is not a postcode lookup', so an agent can rule out postcode_lookup 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?

Gives explicit ordering guidance: 'Use it before local_authority_traffic_totals or traffic_count_points_in_council', naming both downstream alternatives and the sequencing condition. It also states a when-not ('not a postcode lookup') and the geographic scope (Great Britain, as DfT lists them), including former councils for older years.

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