save_scene

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

Annotations say readOnlyHint=false and destructiveHint=false; the description adds the critical nuance that an existing scene with the same name is replaced, i.e. silent overwrite with no confirmation. That is real behavioral context beyond the structured fields. It stops short of saying whether the save persists across restarts or what happens on invalid names.

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?

A single sentence with the verb front-loaded and the overwrite caveat appended where it is most needed. No filler, no restatement of the tool name.

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?

An output schema exists, so return values need not be explained, and there is only one parameter. The definition covers the main risk (overwriting a same-named scene). It is slightly thin on persistence scope (scene stored on device vs. app session) for a stateful feature that pairs with recall_scene.

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?

The schema has one parameter with 0% description coverage, so the description must compensate. It does partially: 'under a name' plus 'replacing any scene with that name' establishes that name is the lookup key used for overwrite. It gives no constraints on format, uniqueness, length, or case sensitivity.

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?

Specific verb+resource: 'Save the light's current look under a name' tells the agent exactly what is captured and stored. It implicitly contrasts with sibling recall_scene (storing vs restoring) but never names it, so differentiation is inferred rather than stated.

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?

Phrasing ('current look') implies the tool is used to snapshot the present state, which is enough to pick it over the set_* tools. However, there is no explicit 'use this when...' guidance, no mention of recall_scene as the counterpart, and no stated prerequisites or limits.

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