sky_set

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

Annotations already cover the safety profile (mutation, non-destructive, not open-world), so the description needn't restate that. What it omits is the behavior that matters for a stateful setter: whether unspecified attributes are preserved or reset, whether the change is transient or requires sky_save to persist, and what happens on an invalid attribute name given additionalProperties=true. For a scene-mutating tool these are real gaps, so it adds little beyond the annotation baseline.

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 dense sentence with no filler; the most-relevant common attributes come first and the niche procedural block is deferred to the end. What it lacks is any structural separation between the two attribute groups, which would have aided scanning, but nothing is wasted.

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 no explanation. But for a mutation tool taking an untyped free-form attribute bag plus an undocumented ref, the description should still say how attributes merge with existing state, what ref defaults to when null, and roughly what the accepted value shapes/ranges are. None of that is present.

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 0% and 'attributes' is a free-form object with additionalProperties=true, so the description's enumeration of keys is the only documentation of the nested payload — that is real added value. However, the 'ref' parameter is left completely unexplained (integer|string|null with no hint whether it targets a sky by name, index, or the active sky), and values get no types or ranges beyond 'rotation (degrees)'.

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?

A clear verb+resource ('Set sky attributes') followed by an enumeration of the specific knobs it touches, including mode enum values and the procedural-sky sub-group. An agent can tell this apart from sky_get/sky_load/sky_save by name alone. It stops short of explicitly naming those siblings or stating how it differs from sky_set_background_image, which is the one adjacent tool it could be confused with.

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?

Usage is only implied through the attribute list; the phrase 'for a procedural sky time, day, latitude...' hints that some attributes are mode-conditional, which is genuinely useful context. But there is no explicit when-to-use, no prerequisites (does a sky need to exist? does it need to be the active sky?), and no routing to sky_load or sky_set_background_image for cases this tool doesn't cover.

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