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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the baseline is low-hanging. The description adds real value beyond them: nearest-first ordering with distances in km, the 250 km default / 5000 km max radius, the 'where published' caveat on wave technology, and disclosure that each record carries a last-checked date and its sources. It still doesn't say how large the full result set is or whether output is truncated.

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?

Appropriately front-loaded and free of filler, but the first sentence is a long run-on that packs example pool names and a full field inventory into one breath, which costs scanability. Splitting the field list from the identity sentence would make it easier to parse.

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 six optional parameters and no output schema, the description does the work of describing the return shape (city, country, coordinates, technology, levels, website, notes, last-checked date, sources), which is exactly what's needed. Feedback coverage is slightly incomplete on result-size limits and on what a town-slug search does when nothing is within radius.

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 the baseline is 3, but the description adds combination semantics the schema does not state — the four mutually exclusive search modes including 'nothing for all of them' — and confirms nearest-first ordering with km values for town searches. The level filter is only lightly touched ('good for beginners and for training') compared to the explicit enum in the schema.

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?

Names a concrete resource (public wave pools/surf lakes) with named real-world examples and enumerates the returned fields, so the agent knows exactly what this returns. It never names a sibling tool to differentiate itself, but the inland/public-pool scope is specific enough to separate it from generic spot or cam tools.

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 clear invocation contexts (town slug, lat/lng, country code, or no argument for everything) and adds a genuine selection cue: pools are inland, work when the sea is flat, and suit beginners/training. It stops short of explicitly naming alternatives such as find_surf_spots or surf_cams, so the when-not guidance is implied rather than stated.

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