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

Beyond the standard read-only annotations, the description discloses key behavioral traits of the function: it actively *build* a pack rather than just returning raw data, and it provides the specific resource path format ('resources/read bugtape://bugs/{bugId}/repro'), which is crucial for understanding the tool's internal workflow.

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 highly dense and professional, front-loading the core concept of building an agent-ready package. The language is precise, with every clause serving to clarify the scope or method of operation.

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 complexity implied by building a 'reproduction pack,' the description covers the function's intent, input constraints, and structural behavior (evidence vs. inference). It provides sufficient context for an agent to call the tool correctly without needing an output schema.

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?

Although schema coverage is 100%, the description adds vital semantic meaning to the parameters, particularly regarding 'occurrenceId,' explaining that it is used to 'Pin to one occurrence' and prevent interleaving. This functional guidance goes significantly beyond merely listing parameter names.

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 uses specific terminology ('agent-consumable reproduction pack') and clearly differentiates the output structure into 'evidence' and 'AI summary' (inference). This distinct definition sets it apart from simple retrieval tools like get_bug_events or get_bug_history.

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 provides explicit guidance on preference and constraint: 'Prefer occurrenceId so sessions are not interleaved' and clarifies what it is NOT ('Not raw rrweb'). This proactively guides the agent on the best way to use the tool compared to simpler retrieval methods.

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