set_effect

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

With no annotations, the description carries the full burden and does meaningful work: it discloses that ten effects loop until stopped, that sunrise/sunset ramp over duration_minutes, and that unsupported lights are silently skipped. It still omits whether effects persist across restarts or require specific permissions, but the operational behavior is well covered.

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 core action and stop condition, then the effect taxonomy. The run-on list of looping effects is a bit dense but every clause conveys non-obvious behavior; no filler sentences.

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 described. For a 5-parameter tool with no annotations, the description covers effect behavior, stopping, and unsupported-light handling adequately; only permissions and persistence are unaddressed.

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 80% and already documents speed's range and duration_minutes' requirement, so the baseline would be 3. The description adds genuine meaning beyond the schema by classifying which enum values loop (candle, fire, ... enchant) versus ramp (sunrise, sunset) and by giving the semantic meaning of "none" as the stop command.

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+resource: start a light effect, or stop effects with "none". It enumerates the effect vocabulary and distinguishes the two behavior families (looping vs. gradual), so an agent can tell it apart from set_lights, set_power, and activate_scene without opening the 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?

The description implies when to use it via the effect list and the parenthetical use cases ("wake-up light, falling asleep"), and it clarifies that "none" is the stop mechanism. However, it never says when to prefer this over set_lights, set_power, or activate_scene, nor any prerequisites, so routing is left to inference.

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