recommend_next_step

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

The readOnlyHint annotation already signals a safe read operation, and the word 'recommend' is consistent with that. However, the description adds no extra behavioral context, such as whether the recommendation is heuristic-based or what factors influence it.

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 with no fluff or unnecessary words. It is concise and clearly structured, though it could benefit from more detail elsewhere.

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?

Given the tool has 11 parameters, 7 enum stages, no output schema, and only a readOnly annotation, the description is too sparse. It does not explain what the recommendation looks like, what inputs are needed, or any constraints on the workflow signals.

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 description provides no parameter-level guidance for any of the 11 parameters. With schema description coverage at 0%, the description should compensate but simply says 'from lightweight workflow signals' without explaining individual fields like currentStage or taskStatus.

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 verb 'recommend', the object 'next reverse-engineering action', and the context 'from lightweight workflow signals'. This distinguishes it from sibling tools like run_reverse_agent which would execute, not recommend.

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 use when you have lightweight workflow signals and need a next action, but it does not explicitly state when to use this tool vs alternatives or provide exclusions. No alternative tool is named.

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