cs_agent_create

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

Annotations indicate a write operation (readOnlyHint false) and non-destructive (destructiveHint false). The description adds that the agent is 'managed' and self-contained, implying lifecycle tracking, and mandates a prerequisite call. However, it does not disclose return values, failure modes, or resource implications, so only moderate transparency beyond annotations.

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?

Two sentences, direct, front-loaded with the action and purpose. No filler or redundant information.

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, a nested object, and no output schema. While the schema is detailed, the description omits what the tool returns (e.g., agent ID) and how to interact with the created agent via sibling tools. This is a notable gap for an AI agent.

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 already covers 100% of parameters, so baseline is 3. The description adds value by explaining that the agent parameter must come from cs_agent_capabilities, complementing the schema's description of 'agent' as a configured local agent name.

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 it creates a managed child agent and specifies suitable use cases (parallel work, different runtime, specialization, independent review). It distinguishes from sibling messaging/status tools by focusing on the creation action.

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?

Explicitly instructs to call cs_agent_capabilities before choosing an agent, and warns against delegating trivial or tightly coupled work. This provides clear when-to-use and when-not-to-use guidance.

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