Get the last engine crash backtrace

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

No annotations exist, so description carries full burden. It discloses that the tool returns crash data from the last crash, and is empty if no crash occurred. It implies read-only behavior but does not explicitly state if calling is safe or has side effects. Adequate.

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 concise sentences: first states what it returns, second provides usage context and edge case. No filler, front-loaded with key information.

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 tool's simplicity (one parameter, no output schema), the description covers return values, usage scenario, and empty state. No additional details needed for a tool of this complexity.

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 single parameter 'instance' is not explained in the description. Schema coverage is 0% (since description doesn't mention it). The schema defines it as integer with default 1, but lack of description adds no clarity on its role (e.g., which instance, index).

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 specifies the return values (signal, faulting address, symbolized backtrace) and the resource (bridge's crash handler). It clearly distinguishes from sibling tools which do not relate to crash retrieval.

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 use case: 'Use this when an instance dies unexpectedly — e.g. run_command reports the bridge closed.' Also mentions empty result if not crashed. No explicit alternatives, but no other sibling tool serves this purpose.

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