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

Annotations already declare non-read-only, idempotent, non-destructive behavior. The description adds useful context beyond them: the created Agent is unpublished, the response includes the saved draft, request key and replay status, and identical data with the original key replays the original creation.

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, front-loaded with the core action and return behavior, followed by the key sibling distinction and idempotency note. There is 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?

With only two required parameters, full schema description coverage, annotations, and an output schema, the description is complete enough. It covers the creation behavior, unpublished state, return essentials and idempotent replay semantics.

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 the schema carries the basic parameter documentation. The description adds meaningful replay semantics for request_key, clarifying that identical data with the original client-generated key replays the original creation.

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The description states a specific verb and resource: creates a new unpublished Agent and returns its saved draft. It also explicitly distinguishes this creation operation from agent_draft_read and agent_draft_edit, which operate on existing Agents.

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 clearly implies when to use this tool by contrasting it with draft read/edit tools for existing Agents, and it explains the retry/replay case with the original request key. It does not explicitly name all alternatives, but the creation-vs-existing-draft distinction is clear.

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