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

Annotations only cover the safety profile (write, non-destructive, closed-world), while the description adds substantial behavioral detail: the result is a DRAFT subject to agent cap / build envelope / mandatory policies, tests are copied into the new suite, integration groups are reported as attached or not_connected, and the return payload is the agent id plus checklist.

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?

Front-loaded with the core action, then layered with side effects and return value in three dense sentences; nearly every clause earns its place. Slightly heavy on parenthetical asides, but no filler.

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?

Despite no output schema, the description names the return value (agent id and checklist) and covers gating, side effects, and integration attachment outcomes. For a 3-param mutation tool with a nested object, this is complete enough to call 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%, so key, name, and integrations are already documented in the schema (including the default-integration-account semantics). The description adds only marginal parameter context ('per the Blueprint's integration groups'), which is the expected baseline when the schema carries the load.

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?

Specific verb+resource with a clear scope modifier: create a DRAFT agent from a Blueprint. It explicitly distinguishes itself from the closest sibling by naming create_agent as the gate-sharer and highlights what is inherited (instructions, model, tools, settings, tests), so an agent can tell it apart from create_agent/build_agent without opening a schema.

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?

It gives strong context: draft-only output, same gates as create_agent, and that only already-connected integrations get attached. However, it never states the inverse condition explicitly (e.g. 'use create_agent instead when you have no Blueprint key'), leaving the create_agent-vs-this choice partly inferential.

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