Subscribe to a named viewer event stream, such as StartupState or LLAutopilot, to capture bounded events locally before reading them.
Subscribe to a named viewer event stream, such as StartupState or LLAutopilot. Events are bounded and remain local until read.
| Name | Required | Description | Default |
|---|---|---|---|
| source | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds genuine behavioral context beyond the annotations: events are bounded and stay local until read, which describes buffering and locality. However, it says nothing about the destructiveHint=true / openWorldHint=true profile — notably whether subscribing replaces or discards an existing subscription or buffered events, which is exactly what an agent needs given the destructive flag.
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?
Two tight sentences, front-loaded with the verb and resource, with the buffering caveat second. No filler or redundancy.
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?
A one-parameter, no-output-schema tool; the description covers what it does, example inputs, and event lifecycle behavior. The main gap is how subscribed events are retrieved (events_read) and what a subscription costs, but the core is adequately covered.
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%, so the description carries the burden — and it does, supplying two concrete valid values for the otherwise opaque 'source' parameter. It stops short of listing all valid stream names or the format, but the examples materially compensate for the undocumented schema.
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 ('Subscribe to a named viewer event stream') and gives concrete stream examples (StartupState, LLAutopilot). It implicitly separates itself from events_read and events_unsubscribe, though it never names those siblings explicitly.
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?
No when-to-use, prerequisites, or named alternatives are given. The pairing with events_read/events_unsubscribe must be inferred entirely from sibling names.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.