start_review

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

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses that no background Claude/LLM job is started and that there is no Claude Code CLI dependency. However, it does not describe side effects such as repeated calls, registration counters, or what happens internally after invocation, leaving some behavioral uncertainty for an orchestration 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?

The description is very concise and well-structured, with the primary action stated first, followed by key behavioral notes and monitoring pointers. Every sentence earns its place, and there is no filler or redundant restatement of the tool name.

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 an orchestration tool, the description covers what to do, what not to do, parameter roles, and where to check progress. It relies on the output schema for playbook steps and does not mention prerequisites or repeated-call behavior, which is a minor gap for an agent that needs to invoke it correctly.

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%, but the description adds meaning for model, effort, and max_turns by stating they are compatibility hints and host-decided. It does not add semantic guidance for the required case_id parameter, such as requiring an existing case. This partially compensates for low schema coverage but not completely.

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 action: 下发标准阅卷 playbook and instructs the host agent to follow the steps. It also clearly distinguishes itself from the legacy background-job behavior by stating 不再启动后台 Claude/LLM job, which clarifies the tool's orchestration role. However, it does not explicitly differentiate from sibling tools like get_review_progress, though the orchestration purpose is fairly apparent.

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 directs progress monitoring to get_case_status / get_workspace_summary, so the agent knows start_review is not for checking progress. It also clarifies that model/effort/max_turns are host-decided and only retained as compatibility hints, preventing misuse. An explicit 'when not to use' beyond progress monitoring is absent, but the context is otherwise clear.

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