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

Annotations already declare non-readonly, non-idempotent, open-world behavior, and the description reinforces this with exactly-once semantics, a no-retry rule after ambiguous delivery, and secrecy handling for the returned key ('keep the key private', configure client only with user approval). The ambiguous-delivery warning is real behavioral guidance that annotations cannot express.

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 short sentences, well front-loaded: the action first, then the no-retry rule and status alternative, then the privacy handling. Every sentence carries instruction, with only minor redundancy between the retry rule and the private-key note.

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 one-parameter, non-idempotent mutation with no output schema, the description covers preconditions, the exactly-once contract, retry behavior, and what is delivered. Nothing an agent needs to invoke it safely is missing.

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% with a single required parameter, and the schema already states 'Private onboarding token. Never show it to the human or log it.' The description adds no further syntax or format detail about the token, so the baseline 3 applies.

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?

States a specific action (deliver a dedicated revocable inference key) scoped to 'exactly once after human approval and active entitlement', which is a concrete verb+resource. It also implicitly distinguishes itself from get_onboarding_status by telling the caller to 'check status instead'. Slightly abstract phrasing ('inference key') keeps it from a full 5, but an agent can tell what this does.

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?

Explicit precondition (human approval plus active entitlement) and an explicit failure/alternative route: 'Never retry after issuance or ambiguous delivery; check status instead.' That names the condition and routes to the correct sibling instead of blind retries.

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