unreal_verify

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

Annotations only declare read-only and non-destructive behavior; the description adds substantial operational detail: per-check result states, a 20-selected-actor limit, 'missing evidence never passes,' world-axis bounds instead of collision clearance, and identity/revision behavior after edits. This is exactly the kind of non-obvious behavior an agent needs and goes well beyond the annotations.

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?

Five dense sentences, front-loaded with the core operation, followed by constraints and edge cases. Every sentence contributes new information and none merely repeats schema or annotation content. The size is appropriate for a verification tool with multiple check types and revision-sensitive behavior.

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?

Given the rich input schema, output schema, and read-only annotations, the description covers purpose, invocation context, result semantics, and key edge cases. It could be slightly more complete by explicitly naming sibling alternatives and clarifying how to obtain the pre-edit identity, but nothing essential for selecting the tool is missing.

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 0%, so the description must compensate. It does add meaning: it clarifies expected_identity/expected_revision semantics ('pre-edit identity ... not its old revision'), defines how gap axes are measured, and caps verification at 20 selected actors. It does not walk through every nested check field, but the schema's detailed titles, defaults, and discriminator carry much of that load.

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 verb and resource: 'Read exact actors again and check explicit transforms, bounds, gaps, materials or labels.' It also states the result vocabulary (passed/failed/unverifiable per check), which sharply separates verification from preview, apply, or inspection tools among the siblings.

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?

It gives a concrete invocation context: after an edit, use the pre-edit identity but not the old revision, because edits change revisions. It also provides exclusions ('checks supplied requirements locally; it does not infer them or run gameplay'), so an agent knows this is not for inferred validation or gameplay simulation. It stops short of explicitly naming sibling alternatives, but the context is clear.

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