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

Annotations already cover the safety profile (read-only, idempotent, open-world), so the description's added value is the geographic coverage ceiling (US and UK only, Overture data) and the shape of the answer (total, category breakdown, top-confidence places). It could have noted behaviour for large areas or cost/latency, but the material constraints are disclosed.

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 action and scope, then return shape, then intent examples — a sensible ordering. It runs a touch long with three example questions that partly restate each other, but no sentence is redundant.

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 spends words on what comes back (total, breakdown, top places) and on the dataset's country limitation. The only real gap is guidance for combining or conflicting area selectors, which the schema hints at but doesn't fully resolve.

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 baseline is 3; the description still adds by framing bbox, near+radius_m, and city as mutually exclusive area selectors and flagging that category is optional and single-valued. That synthesis isn't spelled out in any one schema field, which earns it above baseline.

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 concrete verb pair (count and list), a concrete resource (businesses and points of interest), and an explicit scope (area-based: bbox, radius, or whole city; US and UK only). That area-based framing is what separates it from keyword-style siblings like places_search and places_by_domain, even though they aren't named.

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?

Three worked example questions ('how many restaurants are in this bbox', 'what kinds of businesses are within 500 m', 'how many gyms are in Manchester') make the triggering intent unmistakable. It stops short of naming alternatives or stating when NOT to use it (e.g. lookup by name rather than area).

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