diagnose_crash

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

No annotations are provided, so the description carries the full burden. It discloses the action (auto-read and decode) but lacks details on prerequisites (e.g., target must be halted), side effects, or limitations. The behavioral transparency is adequate but not thorough.

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 single sentence that is front-loaded with the core action. It is concise with no unnecessary words, though it could include more contextual details without becoming verbose.

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 no output schema, the description should clarify what the tool returns. It states it 'reads and decodes' but does not specify the output format (e.g., text, structured data). This missing detail reduces completeness for a tool with multiple read targets.

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?

With 0 parameters, the input schema provides no guidance. The description adds meaning by specifying which registers and structures are read (CFSR, HFSR, MMFAR, BFAR, exception stack frame, recent errors), fulfilling the need beyond the schema. Baseline is 4 due to zero parameters.

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 auto-reads and decodes specific ARM Cortex-M fault registers (CFSR, HFSR, MMFAR, BFAR), exception stack frame, and recent errors. This specific verb+resource combination distinguishes it from siblings like 'read_registers' (generic register read) and 'gdb_backtrace' (backtrace).

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 implies usage when diagnosing crashes but does not explicitly state when to use this tool versus alternatives like 'gdb_backtrace' or 'read_registers'. No exclusions or prerequisites are mentioned.

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