vfx_delete

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

With no annotations, the description carries the full burden and does well: it declares irreversibility ('no undo') and non-cascading side effects (a bake survives node deletion, the Roblox asset survives). It omits behavior on failure (missing name), permission requirements, and what confirmation/response to expect.

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, no filler. The destructive action is front-loaded and the constraints follow, so the agent reads the risk before the conditions.

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?

For a destructive two-parameter tool with no annotations and no output schema, the definition covers scope, target formats, irreversibility, and survival of related artifacts. Missing only error/failure behavior and any confirmation return semantics.

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 only 50% (the enum for 'kind' is undocumented in the schema), but the description compensates by explaining both enum values and what 'name' refers to in each case. This adds real meaning beyond the schema rather than restating it.

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?

States a specific verb (deletes) plus both resource variants it handles, and maps each to a concrete file path (shaders/<name>.wgsl vs bakes/<name>.png plus recipe). This clearly separates it from the read/write/upload 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?

Gives an explicit gate: 'Only on the developer's request', which tells the agent not to invoke it speculatively. It does not name an alternative (e.g. which tool to use instead to remove or revert a shader), leaving that inference to the sibling list.

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