Query the agent event stream for a room. Returns recent observability events emitted by agents, filterable by severity and category.
| Name | Required | Description | Default |
|---|---|---|---|
| appId | Yes | App ID | |
| limit | No | Maximum number of events to return (default: 20) | |
| roomId | Yes | Room ID | |
| category | No | Filter by event category (e.g., 'tool_call', 'decision', 'state_change') | |
| severity | No | Filter by severity level |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden. It explicitly says 'Query' and 'Returns', indicating a read-only operation, and mentions 'recent' and filterability. However, it does not disclose return format, ordering, pagination behavior, or potential side effects, leaving some behavioral gaps.
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?
The description is a single, front-loaded sentence with no wasted words. It immediately states the action and resource, then adds key features (recent events, filtering) efficiently.
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?
The description is adequate for a read-only list tool, but without an output schema, it leaves the agent guessing about the event structure. It also lacks details on event time window, ordering, or whether events are persisted. Overall, it provides the essentials but not full completeness for an observability tool.
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?
The schema covers 100% of parameters with descriptions. The description merely reiterates 'filterable by severity and category' which aligns with schema properties but adds no extra semantic value beyond what the schema provides.
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 clearly states the tool's function: 'Query the agent event stream for a room' with a specific verb and resource. It distinguishes from sibling list tools by focusing on agent observability events, making it unique among the 'list_*' tools.
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 usage for retrieving observability events but does not explicitly state when to use it over alternatives or when not to use it. There is no mention of exclusions or contextual cues beyond 'recent observability events.'
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools follow a clear resource-action pattern, but create_actor, create_agent, and create_orchestrator could be confused, as agents and orchestrators are specialized actors. Similarly, publish and dispatch_task both send messages to topics, though descriptions clarify. Overall, boundaries are mostly distinct.
All tools use the nolag_ prefix with consistent verb_noun snake_case naming. Verbs include create, delete, get, list, update, set, retry, dispatch, publish, generate, and configure. No mixed conventions are present.
At 35 tools, this server exceeds the recommended range for a typical MCP server. While each tool serves a purpose, many CRUD operations could be consolidated (e.g., create_actor, create_agent, and create_orchestrator could be one tool with a type parameter). The count feels heavy.
The toolset covers core lifecycle operations for apps, actors, rooms, scopes, and webhooks, plus messaging, task dispatch, blackboard state, and agent event streaming. Minor gaps exist (no explicit agent-specific update, no webhook delete), but agents can work around these with general actor/app operations.
