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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, so the write profile is covered; the description adds genuinely non-obvious behavior: the created agent is inert (receives no requests) until a runtime connects, all its traffic flows through the entry pipeline, and routing is configured via a branch on /agent/slug or a delegate pipeline. That is substantive beyond the annotations, though it says nothing about what the create response contains or how to identify the new agent.

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?

Three sentences, verb front-loaded in sentence one, and no filler. The density of domain terms (entry pipeline, branch, delegate) makes the tail slightly opaque, but each sentence carries operational information rather than restating the name.

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 no output schema, the description should say what comes back (agent id/slug, initial inactive state) so the agent can chain into create_agent_instance or configure the entry pipeline. It covers the post-create wiring conceptually but omits the response shape, leaving a real gap for a 3-param creation tool.

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 already documents slug, name and kind including the 'fixed for good' immutability of kind. The description adds only an indirect gloss on slug semantics via the '/agent/slug' branch reference. Baseline 3 applies when the schema carries the parameter burden.

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?

Opens with a specific verb+resource ('Create an agent') and immediately scopes it against the runtime-connection siblings (withhuman CLI, create_agent_instance, create_provisioner_token), so an agent can tell this is the bare agent-entity creation step rather than the runtime wiring step. It stops short of a full one-line differentiation sentence, but the boundary with siblings is recoverable from the text.

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?

Gives clear sequencing context ('nothing reaches it until a runtime is connected') and routes the agent to the correct follow-up tools depending on deployment model — the CLI when self-hosting on the machine, create_agent_instance/create_provisioner_token for a service you run. No explicit when-not-to-use or prerequisites like org permissions are stated, so it stops short of a 5.

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