build_minimap

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

The description states the tool is a read-only probe: it 'does the headless-safe part for real (resolves the editor world, detects World Partition, and ... reads back whether a minimap texture already exists) and returns built=false with a note.' This directly contradicts the annotations readOnlyHint=false and destructiveHint=true, which tell the agent the call may destructively mutate the environment. Despite being otherwise unusually candid about GPU/commandlet gating, the conflict with structured fields is a serious false signal.

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?

Structure is good — purpose first, then the gate, then behavior, then the return shape. However, the middle of the description is weighed down by implementation trivia that does not help an agent decide or invoke anything (FWorldPartitionMiniMapHelper::CaptureBoundsMiniMapToTexture, ASceneCapture2D, RequiresCommandletRendering(), the -AllowCommandletRendering flag).

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 compensates by enumerating the return shape ({ world, is_world_partition, built, already_has_minimap?, success, note, message }) plus explaining why built will be false. Combined with the explicit statement of what real work it performs, an agent has enough to call it and interpret the result; only the annotation conflict leaves residual ambiguity.

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?

The tool takes zero parameters, so there is no parameter semantics to document; the baseline for a 0-param tool applies. Nothing in the description misrepresents the (empty) input contract.

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 opening sentence gives a specific verb+resource: 'Reports whether a World Partition minimap can be / has been built for the current editor world.' It also implicitly disambiguates itself from sibling build_* tools (build_hlod, build_lighting) by making clear it is a status report rather than an actual build, though it never names an alternative tool explicitly.

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: an agent can infer this is a pre-flight gate you call to learn whether a minimap exists or can be generated, and that real generation cannot be driven from one request. But there is no explicit 'use this instead of X when Y' routing, and no named sibling for the actual build path.

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