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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. Beyond that the description adds genuine context: staff-only authorization, the delta semantics of newFromCustomer relative to the last read, and the long-poll wait behavior. It stops short of describing failure modes or cursor staleness handling, so a 4 rather than 5.

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?

It is a single dense paragraph, front-loaded with the access restriction and the scope, then the return contents, then the call pattern. Every sentence carries information, though the long inventory of returned fields runs close to list-dumping rather than tight prose.

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 must carry return-shape information and it does: it names the customer-progress signals, build log, brand, sent cards, and the newFromCustomer delta. What is missing is any sense of the response structure or how large these sections can get, but for a 3-parameter read tool this is close to sufficient.

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%, so the baseline is 3 and the schema already documents all three parameters. The description still adds value by explaining the intent behind two of them — the cursor round-trip for since and using waitSeconds to wait rather than poll — which is rationale the schema text does not supply.

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 ('Everything about one agent onboarding in a single read') and enumerates the concrete payload it returns (customer progress, build progress/log, brand, cards, newFromCustomer). That enumeration meaningfully separates it from generic onboarding readers, though it never names the adjacent siblings like get_customer_onboarding or get_onboarding_status.

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 real operational guidance for the cursor/wait pattern ('Pass back the returned cursor as since; pass waitSeconds to wait for the customer instead of polling') and a hard access constraint (oriiion STAFF ONLY). However, it never says when to prefer this over sibling readers such as get_onboarding_status or onboarding_v7, so alternative-selection is left to inference.

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