Export Trace as Text

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

The description adds significant behavioral context beyond annotations: it waits for trace completion via websocket, can clear trace from memory with release, and explains the 409 conflict during runtime. Annotations already indicate read-only and idempotent, but the description provides the actual mechanism.

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 informative and well-structured, front-loading the core purpose. It is somewhat long but each sentence adds necessary detail about waiting, release, tableId, and timeout. Minor redundancy but overall efficient.

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?

Given the tool's complexity (7 params, 1 required, no output schema), the description covers the essential behavioral nuances like waiting, release, and tableId for cross-process scenarios. It does not detail the output format but that is documented in the response_format parameter. Overall sufficiently complete for an export 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?

Schema coverage is high (86%), so baseline is 3. The description adds value beyond schema for key parameters: it clarifies tableId's optionality under different scenarios, wait's default behavior, and waitTimeoutMs's default/cap. For other params like response_format and showRealNumbers, it adds little.

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 exports a trace as plain text and returns full trace content. The verb 'export' and resource 'trace' are specific, and it distinguishes from sibling tools like openl_cancel_trace or openl_get_trace_nodes by focusing on the complete export.

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 explains when to use it (after starting a trace, during a running trace it handles 409 by waiting via websocket) and when to pass tableId (for traces started by other processes). It does not explicitly compare to alternative tools but provides enough context for the typical workflow.

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