skylight_undo_auto_creation

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is known. The description adds genuinely useful scope beyond that: the destruction covers both the intent and its drafts, not just the intent. It still omits whether the action is reversible, what permission level is needed, and what happens to an already-approved intent.

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 tight sentence with the destructive verb front-loaded and no filler. It is appropriately sized for the amount of information it chooses to convey, though brevity here is partly a symptom of under-specification.

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 destructive, open-world mutation with no output schema and zero parameter documentation, the description is too thin. It says what is discarded but not which argument identifies the target, whether the operation can be retried, or what a caller should do on failure.

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 0% and the description explains neither the required 'id' nor the optional 'frameId', so an agent cannot tell which identifier is expected (intent id? draft id?) or when frameId matters. With two undocumented parameters, the description fails to compensate for the coverage gap.

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 pair (undo/discard) and a specific resource (an AI auto-creation intent and its drafts), which is clearer than most siblings. It does not, however, name or contrast itself against the adjacent tools skylight_approve_auto_creation or skylight_get_auto_creation_intent, so the agent must infer the boundary itself.

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?

There is no when-to-use guidance at all — nothing says to use this instead of approving, ignoring, or re-listing an intent. The agent is left to infer that this is the rejection path for an intent it has already fetched.

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