save_decoration

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

Annotations already declare readOnlyHint=false and destructiveHint=true; the description usefully discloses that state is harvested from the ``.kiln_recipe.json`` sidecar and that omitted params fall back to sidecar values then defaults. It does not, however, explain the destructive aspect — what happens on a name collision, whether an existing library entry is replaced, or where the library lives — which is the one behavior the agent most needs before calling it.

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 opening two paragraphs are well front-loaded and earn their place, but roughly half the text is a parameter list that duplicates a fully-described schema, padding a definition that could be half as long without losing information.

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 10-parameter mutating tool with a destructive hint and no output schema, the definition covers inputs and the returns shape but omits the success/failure semantics (collision handling, required sidecar presence, path errors) that an agent needs to invoke it safely.

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 100%, so the schema already documents every parameter, and the description's ``:param:`` list restates those same texts nearly verbatim. It adds no format, coupling, or validation detail beyond the schema, so the baseline of 3 applies.

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 and resource ("Save a proven decoration to the library") plus the payoff (reuse on future models), and explicitly pairs it with ``apply_decoration``, so it is distinguishable from list_decorations, decoration_info and apply_decoration without opening a schema.

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?

Implies the timing ("proven decoration", "model that was just decorated") and names the follow-up tool ``apply_decoration``, but never states when not to use it — e.g. whether a repeat name overwrites an existing library entry, or whether presets (create_decoration_preset) are the better choice.

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