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

Annotations already establish readOnly/idempotent/non-destructive, so the description's job is to add semantics beyond that. It does: data provenance (police.uk per 1,000 residents, Land Registry median sold price, Ofsted Outstanding), the flats exclusion, and that ranks are London-wide rather than within the borough filter. It doesn't describe the returned row shape, but annotations carry the safety profile.

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?

A single dense paragraph that front-loads the metric list, with no filler sentences. It is slightly long because of the parenthetical source annotations, but every clause carries information an agent needs to pick a metric correctly.

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?

For a 6-parameter read-only ranking tool with no output schema, the description covers metric semantics, the hub dependency, the cut-off, and the scope of ranking. The main remaining gap is the shape of returned rows (district name, score, rank), which an agent must infer.

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 3 is the baseline, but the description adds meaning beyond the schema: it defines what each metric rank actually measures and clarifies that reverse yields 'most expensive, highest crime, longest commute first', and that hub is required for shortest_commute. These tie parameters to behavior rather than restating field names.

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 (rank) and resource (London postcode districts) plus the exact set of ranking metrics with their data sources. An agent can immediately distinguish it from compare_london_districts or find_london_district, which are lookups rather than rankings.

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?

Explains each metric's meaning and conditional usage (shortest_commute 'needs hub', flats excluded from cheapest_houses), and describes the optional borough filter and reverse ordering. It does not explicitly name a sibling tool or say when to prefer this over compare_london_districts, so it stops short of a 5.

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