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

Annotations already declare readOnly/openWorld=false safety, but the description adds real behavioral context: money is duplicated as formatted vs raw, each receipts entry carries an invoice number, and receiving more than ordered is an allowed overage rather than an error. These are non-obvious semantics an agent could not infer from the schema.

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-loaded with the one-line summary, then layered detail on money fields and receipts. It is a dense paragraph with no filler, though it is longer than strictly necessary and could be split for faster 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?

With no output schema, the description carries the return-shape burden and does so thoroughly: field groups, the ordered vs receipts distinction, the quantity comparison rule, and the overage caveat. An agent can interpret the response without further docs.

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% and the single parameter is already documented in-schema as an id from get_purchase_orders, not a PO number. The description adds no further parameter detail, 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 verb and resource ('One purchase order in full') and enumerates exactly what is included: supplier, outlet, status, ordered lines, and per-delivery receipts. It is clearly a single-record fetch, distinguishing it from the list sibling hub_get_purchase_orders, which the schema also references as the id source.

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 explicit when-not guidance ('ALWAYS CALL THIS AFTER receive_purchase_order instead of retrying the receive') and routes the agent to update_purchase_order for writing the raw *Amount values back. It also frames the questions the tool answers, so selection is unambiguous.

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