list_crashes

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

With no annotations, the description carries the full burden. It discloses the data source (logcat crash buffer), the no-root requirement, platform limitation, substring package filtering behavior, and the return JSON structure. This covers the key behavioral traits for a read-only list tool, though it could mention the meaning of 'recent' or whether ANRs are separate.

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 four concise sentences, front-loaded with the core function. Each sentence earns its place: function + source, platform caveat, filtering behavior, return format, and sibling pointer. No redundancy or 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?

The tool is a simple listing operation, but the description covers source, platform, privilege, filtering, return schema, and the relationship to a sibling tool. It is sufficiently complete for an agent to select and invoke correctly, though it omits details about limit behavior and 'recent' timeframe, which are minor.

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 0%, so the description must compensate. It explicitly explains the package parameter ('substring match on the crashing process'), adding valuable detail. However, limit and device are not described, though device is self-explanatory and limit defaults to 10. The description partially compensates but not fully.

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 exactly what the tool does: 'List recent app crashes and ANRs' with a specific data source and privilege level ('from the logcat crash buffer, no root'). It also distinguishes itself from the sibling tool get_crash, which is referenced for pulling a full stack trace.

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?

It explicitly restricts usage to Android ('Android-only') and explains iOS logs are not exposed, providing a clear when-not-to-use scenario. It also points to get_crash() as an alternative when a full stack is needed, making the choice between list and detail tools explicit.

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