Analyze a .mxdiagnostic payload from MetricKit (production diagnostics)

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

The description discloses aggregation logic, raw binaryUUID+offset inclusion, localized-string handling, and limitations (no symbolication, simulator limitation). However, it does not explicitly state that the tool is read-only or has no side effects. With no annotations, this is a minor gap.

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 relatively long but well-structured, with each sentence providing useful context. A minor reduction could improve conciseness, but it remains effective without redundancy.

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 covers input parameters, output structure (three sections, raw binaryUUID+offset, cross-tool hints), and limitations. It does not detail error handling or invalid payloads, but given the complexity, it provides sufficient completeness for effective use.

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 all 5 parameters (100% coverage). The description adds significant value by explaining the behavior of each parameter, such as the precedence rule for payloadJson over payloadPath, aggregation behavior of payloadDir, and detailed explanation of groupBy enum options with clustering criteria.

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 parses Apple MetricKit .mxdiagnostic payloads from production builds, aggregates crashes, hang hotspots, CPU exceptions, and disk-write exceptions, and returns three actionable sections with cross-tool chaining hints. It distinguishes from sibling tools like analyzeHangs and findCycles by providing specific hints on when to use them.

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 explicitly states that simulator does not generate MetricKit payloads, so it should be framed as post-mortem analysis. It also clarifies that symbolication is a separate tool and provides cross-tool chaining hints, guiding the agent on when to use this tool versus others.

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