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

No annotations are provided, so the description carries full burden. It discloses the historical behavior, the side effect (created second agent with own wallet/identity), and the current behavior (always returns onboarding URL). This is transparent about the retired nature and the change in behavior.

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 long paragraph but each sentence provides essential information: retirement status, reason, and current behavior. It's front-loaded with the '[RETIRED]' tag and clearly explains the situation without excess. Despite its length, every sentence earns its place.

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 11 parameters and no output schema, but the description explains the entire context: the tool is retired, what it used to do, why it's retired, and what it does now. It also provides the alternative path (VIA onboarding URL). This is complete for the agent to understand and use the tool 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 coverage is 100% with detailed descriptions for all 11 parameters. The description adds context that the parameters are historical and may not be used anymore, but the schema already documents each parameter's semantics well. The description compensates by explaining the retirement, which covers the 11 params collectively. Baseline 3 is appropriate since the schema does the heavy lifting, and the description adds the crucial retirement context.

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 is retired and no longer creates anything, explains what it does now (returns VIA onboarding URL), and what it used to do (created a second agent record). This distinguishes it from siblings like create_ref_link and get_concierge_status, and explains the retirement context.

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 says 'Every call now returns the VIA onboarding URL. Send the owner there.' It explains when not to use it (no longer for creation) and directs to VIA as the alternative. This is clear guidance for an agent on what to do with this tool.

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