scene_diff

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

Discloses the snapshot/diff workflow and what changes are detected (added/removed/modified objects, transforms, materials, lights). Annotations already indicate read-only and non-destructive, but description adds functional context.

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 that front-load the purpose and efficiently convey the tool's behavior and parameter role.

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?

Simple tool with one parameter and no output schema. Description covers the core use case and behavioral nuance adequately.

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?

Input schema fully describes the 'action' parameter with enum values and descriptions. Description adds process context but not additional parameter-level meaning beyond schema.

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?

Clearly states verb 'compare' and resource 'scene state over time'. Distinguishes from siblings by describing a two-step process unique among the listed tools.

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?

Explains the required sequence (snapshot then diff) and the auto behavior. No explicit mention of when not to use, but the context of siblings implies uniqueness.

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