Delete Layer State

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

Annotations already flag destructiveHint=true, so the safety profile is covered. The description does add genuinely useful behavior: the refusal path for an unknown name (it lists the saved ones). The trailing "Pack: settings · lean: no" is opaque filler that conveys little an agent can act on.

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?

Front-loaded with the destructive action and its scope, and the layer-vs-state distinction comes early. It is short, but the fragmentary "Pack: settings · lean: no" earns little and reads as internal shorthand.

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 single-parameter tool with an output schema and a destructiveHint annotation, the description covers scope, the layer-safety caveat, and the error path. Only the opaque trailing fragment leaves a gap.

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% and the schema itself says the name must come from layer_state_list. The description reinforces this only indirectly via the refusal clause. Baseline 3 is appropriate when the schema carries the parameter definition.

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 gives a specific verb and resource ("Remove the named state's XRECORD") and immediately separates the tool from layer_delete by stating "Layers themselves are untouched." That contrast makes the resource unambiguous, though the term XRECORD is internal jargon an agent may not know.

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 "Layers themselves are untouched" line implicitly routes the agent away from layer_delete, but there is no explicit when-to-use guidance relative to layer_state_save/layer_state_restore, and no prerequisites stated. Usage is inferable rather than described.

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