Query agent runs and knowledge bases in turn-based sessions to investigate issues and analyze behavior. Ask natural language questions to retrieve traces, monitors, and signals for debugging and monitoring.
Ask a question against the agent's runs / knowledge base (turn-based session)
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | ||
| message | Yes | ||
| max_turns | No | ||
| session_id | No |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint and openWorldHint, so the safety profile is covered. The description adds useful behavioral context by specifying a turn-based session over runs/knowledge base, but it does not disclose how session state behaves, what max_turns does, or what kind of response the caller receives.
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 one front-loaded sentence that conveys purpose, target resource, and session behavior without redundancy. Every word contributes and nothing needs to be trimmed.
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 tool with four parameters, no output schema, and no parameter documentation in the schema, the description is too sparse to be complete. It gives the gist but leaves callers guessing about optional parameter effects and response behavior.
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%, so the description must provide parameter meaning; it partially does by implying 'message' is the asked question and 'turn-based session' relates to session state. It does not explain model or max_turns, leaving two meaningful optional parameters effectively undocumented.
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 that the tool asks a question against the agent's runs/knowledge base and is turn-based, which is far more specific than a tautology. However, it does not explicitly distinguish itself from similar-sounding siblings like cortex_ask, leaving some differentiation to inference.
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 phrase 'turn-based session' hints at multi-turn conversational usage, but there is no guidance about when to use this tool versus alternatives like cortex_ask, when not to use it, or what prerequisites might exist. Agents looking for routing guidance will not find it here.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.