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

Annotations already declare readOnly/non-destructive/idempotent, and the description corroborates rather than contradicts them ('Writes nothing'). Beyond that it discloses non-obvious behavior: default address fallback, delivery pricing coming from Printdash, the resulting order being unpaid with a pay link or held for a Team owner's approval, Australia-only delivery, AUD/GST pricing, and the sign-in gate.

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?

The purpose is front-loaded, but the core is a single sprawling sentence that packs line states, address logic, references, totals, and order outcomes into one list. Nearly every clause carries information, yet the density hurts parseability and the ordering of information is not tuned for scanning.

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?

An output schema exists, so return values need not be explained, and the description covers everything else an agent needs: that it is a read-only preparation step, that a confirmation_token feeds place_order, the authentication requirement, and the geographic/currency constraints.

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 baseline is 3, but the description still adds meaning: the reference is required at checkout and effectively kept to 50 characters, address_id falls back to the context default, po_number applies to a Team on account, and payment_method is a request that Printdash decides on. The one wrinkle is that it calls the reference 'required' while the schema marks no parameters required and caps it at 200.

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 ('Checkout's review of the whole cart in the current buying context') and enumerates exactly what the review surfaces: line artwork state, file notices, delivery/pickup, reference, notes, PO, whitelabel, totals, expected_total. It also draws the boundary with the sibling that acts on the result by naming place_order and the confirmation_token.

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 frames the when: this is the review step, nothing is ordered 'until place_order is called after the customer agrees', and a signed-in account is required or the connection prompts sign-in. It does not, however, say when to reach for get_cart or price_job instead, so the alternative routing is only partial.

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