start_task

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

Annotations only declare it is a non-read-only, non-destructive operation. The description adds materially useful behavior beyond that: it overwrites any previous baseline for the repository, scopes writes to inside the .git directory, and explains what is captured (HEAD plus dirty-file fingerprints). These are exactly the side-effect details an agent needs before calling a mutating tool.

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?

Three compact sentences, all front-loaded: purpose first, then the overwrite side effect, then the write scope. No filler and nothing that restates the name or annotations.

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 two-parameter tool with annotations covering the safety profile, the description provides the essential behavioral caveats. The only gap is that, with no output schema present, the agent gets no hint of what the call returns (e.g., the recorded baseline identifier), which is minor here.

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 100%, so both repo_path and task are already documented in the schema. The description adds no extra syntax, format, or constraint detail for either parameter, so the baseline 3 applies.

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 a specific verb and resource: record a baseline (HEAD + fingerprints of dirty files) before starting work. It clearly frames the tool's role in the verify workflow, which implicitly separates it from verify_task and inspect_task_state, though no sibling is named explicitly.

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 states the trigger condition precisely ('before starting work') and explains why (so later verification attributes only the task's own changes), which tells the agent where this fits relative to verification tools. It does not explicitly name an alternative tool or a when-not-to-use case.

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