find_crashes

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

With no annotations, the description carries the full behavioral burden. It does disclose the output ('whole stack traces') and the data source ('crash buffer'), making the extraction appear non-destructive, but it does not explicitly state whether reading affects the buffer or whether special permissions are needed. It is acceptable but not rich.

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?

One functional sentence plus a compact, well-organized Args block with no filler. Every sentence earns its place and the most important information is front-loaded.

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?

For a straightforward read tool, the description covers purpose, source, output, and all parameters; the output schema further covers return structure. It could add an explicit note about no side effects or when to use alternatives, but nothing necessary for a basic invocation is missing.

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 description coverage is 0%, so the description must define all three parameters, and it does: package restricts matching traces, limit controls trace count, and serial disambiguates devices. This adds real semantic value over the bare property names and types.

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 opening sentence names a specific verb ('extract'), a specific resource ('recent crashes and ANRs'), and the source ('the crash buffer'), which clearly distinguishes it from siblings like read_logs or clear_logs. This is more than a tautology and gives an agent a precise idea of the tool's scope.

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 behavior description implies the tool is for retrieving crash/ANR stack traces, but it never explicitly says when to prefer it over read_logs or capture_* tools, nor does it mention exclusions. This is adequate as an implied usage signal but lacks explicit routing.

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