ground_at

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

No annotations are supplied, so the description carries the full burden; it does clearly convey that this is a non-mutating query and describes the returned semantics in unusual detail (bilinear interpolation, nearest grid point material, sea level handling, highest surface below y). It does not say what happens for out-of-bounds points, empty results, or invalid map keys, and it never states that it is read-only in so many words.

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?

It is a single dense but well-ordered sentence that front-loads the core action ('Ground at up to 1000 points') before listing return facets. Every clause adds information, though the telegraphic semicolon-chained style makes it harder to parse than it needs to be.

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 must describe return values, and it does so thoroughly by enumerating every surface/height facet returned. For a read-only point-query tool with three simple parameters, the only meaningful gap is edge-case behavior (out-of-range coordinates, missing map).

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 67% and the schema gives no description at all for the required 'points' array, so the description does real work: it defines points as (X, Z) pairs and explains that supplying 'y' returns the highest surface below that height, which is the single most important semantic for the optional y field. It only repeats maxItems (1000) and adds nothing new for 'map'/'session', which the schema already documents.

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 operation (sampling ground data at up to 1000 X/Z points) and enumerates exactly what is returned: bilinear terrain height, nearest-grid material/water, sea level, walkable surfaces and building surfaces. An agent can tell this is a batch terrain-query tool rather than an object query. It stops short of naming or contrasting sibling tools such as object_ground or world_info, so it does not earn a 5.

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?

There is no explicit when-to-use or when-not-to-use statement and no mention of the obvious alternatives (object_ground, world_info, check_overlap). The only guidance is implicit: the 'up to 1000 points' framing and the 'y' clause hint at batch height sampling and ground-snapping, but the agent must infer when this beats the sibling tools.

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