exception_autopsy

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

No annotations provided, so description fully shoulders transparency. It declares non-destructive behavior ('peeked, not drained'), clarifies defaults, and describes what the tool collects. No contradiction.

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?

Two sentences: first lists capabilities concisely, second provides usage condition. Every word earns its place. No fluff.

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 3 optional parameters and no output schema or annotations, description covers purpose, parameters, usage guidance, and behavior. Lacks explicit return format, but the list of included context is sufficient for an agent.

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 already describes parameters (100% coverage). Description adds context: defaults (threadId to last-stopped thread, frameCount to 20, maxRecentOutputLines to 50), and explains the 'peek' behavior for output lines. Adds value beyond schema.

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?

Description clearly states 'Full exception context in one call' and enumerates specific components (exception type, inner-exception chain, stack frames, locals, source snippet, output peek). This distinguishes it from sibling tools like stacktrace_get or process_read_output.

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?

Explicit condition 'Call this when state.lastStop.reason == "exception"' guides when to invoke. Also notes non-destructive nature relative to process_read_output, but could further differentiate from other debugging tools.

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