Get or create agent

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

The description supplements annotations (idempotentHint, destructiveHint) with concrete behavior: returning existing agent with 'existing': true, plan limits, model ignored when existing, and mention of reconnection. No contradictions; adds significant context 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?

The description is a single, clear paragraph. It front-loads the purpose and provides necessary details without excessive verbosity. Could be slightly more structured, but highly effective.

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 no output schema, the description adequately explains return behavior (existing flag), idempotency, plan limits, and model handling. It covers all critical aspects for a create/get tool and references relevant siblings (set_agent_model).

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?

Input schema has 100% description coverage, so baseline is 3. The description adds key behavioral details beyond schema: model is ignored when returning an existing agent, and advises using set_agent_model to change it. This enriches parameter understanding.

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's dual purpose: 'Get or create an agent by name'. It specifies the resource (agent) and distinguishes from siblings by emphasizing idempotency and reconnection use case. No ambiguity.

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 states when to use this tool: 'the right way to reconnect to an agent you used before'. It also notes limitations (plan limits, model handling) and directs to use set_agent_model for model changes. This clearly differentiates from alternatives like get_agent or set_agent_model.

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