lightbulb_use_action_capability

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

The description discloses that the destructive/open-world hints are intentionally conservative so the host can apply approval policy, and that RBAC, preview, approval, company-scope, and connector controls still apply — genuine context beyond the raw annotation booleans. No contradiction with the annotations.

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?

Three compact sentences, front-loaded with the core purpose and then adding routing and safety context. No filler, though phrasing like 'conservative host-visible risk hints' and 'destructive/open-world annotation' is jargon-heavy.

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?

Safety and return values are well covered (annotations plus an output schema), but the description doesn't explain where valid capability names come from (e.g., lightbulb_find_capabilities), what format arguments_json expects, or the discovery flow that precedes invocation. For a 2-param generic dispatcher with 0% schema coverage, this leaves agents guessing.

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 never documents the two parameters. The parameter name 'arguments_json' and the phrase 'discovered action' weakly imply that 'name' is the action name and arguments_json carries serialized arguments, but that inference is left entirely to the agent — a real gap for a generic dispatcher.

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?

The description states a specific verb and resource ('Invoke a discovered action') and distinguishes this tool from its read-side sibling via the routing rule 'Any capability without an explicit read-only annotation is routed here.' The meaning is clear, though 'capability/action' remains abstract without context from the find/describe siblings.

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?

It gives an explicit selection condition: capabilities without a read-only annotation are routed here, which implicitly directs read-only ones to lightbulb_use_read_capability. It stops short of naming the alternative explicitly, but the routing rule is actionable on its own.

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