Reset Active Scene

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

Annotations declare destructiveHint=true, so the destructive nature is known. The description goes well beyond: it specifies exactly what gets removed (objects, materials, non-active render data, non-main takes), the undo buffer flush, the full-document swap without prefix, and the performance rationale. This is substantial behavioral context that annotations alone don't provide. The only minor gap is that it doesn't mention return value or errors, but with destructiveHint true and no output schema that's acceptable.

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?

Three sentences, each dense with information, front-loaded with the core behavior and conditional logic, then a performance note. No fluff.

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 it's a destructive tool with two branches (prefix and no-prefix), the description fully specifies what gets removed, the undo flush, the keep_active_rd default, and why it beats remove_entity. The output schema is absent but not needed for a void-ish operation. Complete.

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 coverage is 100% (both params documented), but the description adds crucial semantics: the prefix param's behavior is explained ('removes only objects / materials / non-active render data / non-main takes whose name starts with the prefix'), and the interaction with keep_active_rd (prefix-mode only, default true) is stated. It explains the conditional behavior of prefix vs no prefix in plain language. Adds clear 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?

Description opens with 'Clear scene state in one RPC' — a specific verb and resource. It then distinguishes two modes (prefix vs full reset) with concrete effects: removing objects/materials/render data/takes matching a prefix plus flushing undo, or swapping the active document for a fresh BaseDocument. Clearly distinct from siblings like remove_entity and undo.

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?

Explicitly states when to use each mode — 'with prefix' for targeted cleanup, 'without prefix' for full reset — and names the alternative, remove_entity, with a concrete comparison: 'Much faster than chained remove_entity calls when cleanup involves animated objects.' Gives the exact context (test cleanup) where this tool is appropriate.

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