render_probe

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

Annotations already mark the tool as read-only and non-destructive. The description goes far beyond that, detailing the internal checks (visibility chain, world AABB, frustum test, distance vs far plane, layers vs cull_mask, per-surface material and cull mode) and even the winding-order nuance. It also explains the return value structure ('warnings' list or a verdict). This rich behavioral disclosure is exactly what an agent needs.

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?

The description is long but front-loaded with a clear summary sentence. Every sentence adds technical detail that is useful for a diagnostic tool. It is not terse, but the density is justified for the complexity. It could be tightened slightly, but it is well-structured with a logical flow from purpose to use case to outputs.

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 no output schema, the description fully covers the return value shape. It also explains the exact failure scenario, lists the diagnostic stages, and provides a usage directive. For a tool with 5 parameters and no output schema, the description carries the full burden and succeeds in making the tool's behavior, inputs (via context), and output comprehensible.

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 20% (only 'path' has a description). The tool description does not compensate by explaining how to identify the target node via nth, name, class, or under. Since the description never mentions parameters, the agent gets little help in selecting the correct node argument beyond the schema's single path field.

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 opens with 'Ask WHY a 3D node is or is not on screen, as data instead of pixels,' which is a specific verb+resource combination. It clearly distinguishes the tool from visual debugging tools like screenshot or ui_snapshot, and none of the sibling tools appear to offer the same visibility-chain diagnostic.

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?

The description gives explicit when-to-use guidance: 'USE THIS BEFORE tuning lighting, fog, exposure or palette on anything you cannot clearly see.' It also defines the exact scenario the tool addresses (node exists, visible is true, log is clean, still see nothing). It lacks an explicit 'when not to use' statement or named alternative, but the directive is strong and actionable.

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