aflpp.repro_crash

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

With no annotations provided, the description carries the full burden. It discloses that it captures stdout/stderr and writes a repro bundle under repros/, which are useful side-effect details. However, it does not mention potential side effects of running an arbitrary target command, permission requirements, or behavior on failure, leaving significant gaps.

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 immediately states the action and outcome. Every word contributes to understanding, with no repetition of schema field names or filler.

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 has 5 parameters, no output schema, and no annotations, so the description must provide substantial context. It explains the core action and output bundle but omits critical details like return values, success criteria, failure handling, and parameter semantics. The description is too brief for a tool that executes commands.

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 compensate. It references 'target command' and 'testcase', which loosely maps to target_cmd and finding_id, but it does not clarify the roles of workspace, job_name, timeout_ms, or how the testcase is derived. Parameter meaning is largely left to the reader.

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 uses a specific verb ('Reproduce') and resource ('a finding') with clear mechanics: running the target command with the testcase, capturing stdout/stderr, and writing a repro bundle. This distinguishes it from siblings like crash_report or casr_report, which likely focus on reporting rather than direct reproduction.

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 for reproducing a finding, but provides no explicit guidance on when to use this over alternatives or when not to use it. It lacks comparative context with sibling tools such as crash_report or analyze_testcase.

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