Check reproduction (bug-first)

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true), the description discloses critical behavior: it treats non-zero exit as PASS (bug reproduced) and zero exit as failure to reproduce. This is exactly the kind of non-obvious semantics that the annotation block does not convey, making the description highly transparent.

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 two sentences, front-loaded with the core concept 'Bug-first discipline', and every sentence adds value. It explains what the tool does, the expected input behavior, and the meaning of the result in a compact form.

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 tool that executes a command and returns a pass/fail signal, the description fully captures the necessary context: the expectation of failure, the meaning of a non-zero exit, and the implication for the fixing workflow. The output schema likely covers return values, so nothing else is needed.

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 input schema covers 100% of parameters with descriptions, so the baseline is 3. The description reinforces that repro_command should fail while the bug exists, but it does not add new parameter-level semantics beyond what the schema already provides.

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 runs a command expected to fail and returns PASS only if it fails, which is a specific verb+resource combination. The 'bug-first discipline' framing immediately distinguishes it from the sibling tool verify_done, which is about verification of completion.

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 explicitly says to use it 'before fixing a bug' and warns that if the command passes, you haven't reproduced the bug yet and shouldn't start fixing. This provides clear when-to-use and when-not-to-use guidance, even though it doesn't name an alternative tool.

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