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

Goes beyond the annotations by disclosing duration (~a few minutes), approximate cost (~$0.30), the trigger conditions, and the staff-only access restriction — all genuinely useful for deciding whether to invoke. It is consistent with idempotentHint=false and destructiveHint=true but does not say what happens if the build fails or how to verify completion, a small remaining gap.

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-loads the critical access constraint ('STAFF ONLY') and then the cost/duration, so the highest-value information comes first. The middle sentence is dense with parentheticals but every clause (default trigger, override condition, one-shot semantics) carries decision-relevant information.

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 an async, non-idempotent build trigger with no output schema, the description covers cost, duration, trigger, and one-shot semantics adequately. It could be more complete by pointing at a status/inspection tool (e.g., get_agent_onboarding) for verifying the build, but nothing critical is missing for correct invocation.

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 both parameters are already documented, including the websiteUrl default and the onboardingId provenance. The description only restates 'on a website' and adds no format or fallback detail beyond the schema, so the baseline of 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 verb and resource (start the onboarding account build) and expands the concrete scope of that build: research, brand, images, sources, products, style guide, first posts. It is clearly distinguishable from siblings like finish_agent_onboarding, log_agent_onboarding, and send_agent_onboarding_card.

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?

Explicitly states the default behavior it overrides (build starts on website-card confirmation, or ten minutes after signup for a typed address) and gives the condition for using it instead: 'use this when you have good reason not to wait.' It also notes the one-shot constraint ('Runs once per onboarding'), which prevents redundant calls.

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