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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the mutation safety profile is covered. The description adds valuable behavioral context beyond annotations: the created agent is always a draft, publishing is intentionally outside this tool's scope, and no deploy tool exists. This is exactly the kind of non-obvious behavioral disclosure that helps an agent avoid a wrong workflow.

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 with zero waste. The core action is front-loaded, and the critical constraint (draft-only, no deploy) is stated immediately after. 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?

For a create tool with no output schema and no nested objects, the description covers the essential workflow context: creation always results in a draft, and publishing is a human console action. It doesn't describe the return value, but with no output schema and a simple create operation, that is a minor gap. The sibling context (build_agent, update_agent, activate_deployment) further clarifies where this tool fits.

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 100%, so the schema already documents all four parameters. The description adds no parameter-specific meaning beyond the schema, but it doesn't need to; the schema descriptions are clear. Baseline 3 is appropriate.

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 verb and resource ('Create a new agent') and immediately clarifies the critical scope constraint: it always lands as a draft. This distinguishes it from sibling tools like build_agent, update_agent, and activate_deployment, and makes the tool's purpose unmistakable.

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 when to use this tool (to create an agent) and, more importantly, what not to expect: publishing is a human act in the Nebelus console and no deploy tool exists here. This prevents an agent from searching for a nonexistent publish/deploy step and clearly routes expectations.

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