List / export captured traffic

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

With no annotations provided, the description carries the full behavioral burden, and it performs well. It discloses the transformOutcome values and patchesApplied count available, explicitly states sensitive headers are redacted by default and how to opt into raw values, and explains body preview options. This is substantial behavioral detail that significantly aids agent decision-making. Notably, it doesn't flag any destructive or side-effect behavior, which is important for a read/list operation.

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 tight, information-dense paragraph with zero redundancy. Every sentence adds value: purpose, output traits, redaction behavior, three boolean flag explanations, and export capability. It front-loads the purpose and progressively adds options. No wasted words.

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 read-only listing tool with 100% schema coverage and no output schema required, the description is thorough. It covers the key behavioral concerns (redaction, preview options, export formats), explains output fields (transformOutcome, patchesApplied), and provides the use case. It's complete enough for an agent to confidently select and invoke this 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 100%, so the baseline is 3, and the description adds meaningful value beyond the schema. It clarifies the export parameter's JSON/HAR format rationale (Charles log-export replacement) and explains what includeSensitiveHeaders does in prose (explaining redaction default). The description reinforces parameter purpose and adds context about what each inclusion flag reveals. It loses one point because it doesn't fully clarify the 'filter' parameter semantics beyond what the schema already states.

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 states a clear purpose: inspect captured traffic to confirm a rule matched the intended request. It specifies the tool operates on 'captured traffic' and its sibling context (proxy_list_* tools) distinguishes it from mocks/transforms listing tools. It doesn't explicitly name siblings as alternatives but the context makes differentiation reasonably clear. A specific verb+resource with clear purpose, though it could explicitly distinguish from proxy_list_transforms.

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 implicitly conveys usage context (confirm a rule matched) and explains when to use flags like includeSensitiveHeaders, includeRequestBodyPreviews, and export for JSON/HAR. It doesn't explicitly say when NOT to use this vs alternatives, but the sibling tool names and context strongly imply the alternatives. The export functionality positions it as a replacement for Charles log-export workflow, giving additional context. Could be improved with explicit exclusions but is adequate.

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