get_terrain_grid

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

With no annotations, the description carries the full behavioral burden. It usefully discloses that this is a single-call bulk sampling operation, which layers are returned, and a version prerequisite, but it does not state the read-only nature explicitly, how bounds/caps are enforced, or what the response structure looks like in the absence of an output schema.

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?

Two sentences, front-loaded with the core action and its outputs, with the speed comparison and prerequisite trailing as supporting detail. The phrase 'in one call' is slightly redundant with 'Sample ... into a terrain grid', but nothing else is wasted.

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 an 8-parameter tool with no output schema and no annotations, the description covers purpose, output layers, performance rationale and a version prerequisite. It leaves meaningful gaps around the bounding-box parameters and the max_cells safety cap, which are the most likely source of incorrect invocation for a spatial sampling call.

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 50%, so the description should compensate and largely does not. It adds meaning only for include_heights ('optional ground heights'); step, max_cells and especially the min_x/max_x/min_z/max_z bounds pair are undocumented in both places, and the description never explains what the grid is clipped to or what happens when the cap is hit.

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 gives a concrete verb ('Sample the game's navigation graph') and a concrete output artifact ('terrain grid'), then enumerates the layers produced (walkability, water, roads, building interiors, bridge candidates, optional heights). It clearly separates itself from get_navigation_point by framing itself as a bulk alternative, but it says nothing about the similarly-named sibling get_terrain_report, leaving that distinction ambiguous.

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?

'Much faster than repeated get_navigation_point calls' states the condition that selects this tool over the point-sampling sibling. It also discloses a prerequisite ('needs plugin 0.2'), which is useful usage context. It does not state any when-not-to-use case (e.g. small areas or single-point lookups where the grid would be overkill).

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