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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, open world), so the description is credited for going beyond them. It discloses data provenance that materially affects trust in results: stays and food/surf businesses are saved merged OSM+Overture collections, while 'spots' is a live OpenStreetMap lookup — a meaningful freshness difference between categories. It also specifies the photo sub-object contract ({url, page, author, license}) and licensing condition, which no annotation conveys.

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 category map is front-loaded, which is good, but it is buried inside nested parentheses ('spots (Surf spots (community mapped))') that are hard to parse. The long parenthetical enumeration of stay types (hotels, resorts, hostels, surf camps, guesthouses...) consumes significant space for marginal selection value. The final sentence about photos is useful and earns its place.

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?

There is no output schema, and the description does an unusually good job of describing return payloads: which fields stays carry (website, phone, email, socials, stars, rooms, facilities), and the shape of embedded photos. Combined with the category-to-data-source mapping, an agent knows what it will get back. Minor gaps remain around pagination/limit semantics and the spatial default when radius_km is omitted.

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 only 40%, so the description must compensate. It does useful work by expanding the 'category' enum into readable buckets and describing what data each collection yields (stay fields, photo object shape), but it says nothing about limit behaviour or radius_km even though ordering by distance implies a radius filter. With annotations already declaring readOnly/idempotent/openWorld, the behavioral burden is lighter, hence 3 rather than 4.

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 (places around a surf town) and a specific ordering rule (sorted by distance), then enumerates the five category buckets with their labels. An agent can immediately tell this is a distance-sorted place listing. It stops short of distinguishing itself from the sibling find_surf_spots, whose scope partially overlaps the 'spots' category.

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?

Usage is only implied through the category breakdown; there is no explicit statement of when to choose this over find_surf_spots or search_towns, and no exclusion guidance. An agent can infer this is the tool for lodging/food/coffee/surf-business listings near a known town, but the routing decision against siblings is left to inference.

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