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

Annotations already declare destructiveHint=true, openWorldHint=true and idempotentHint=false, so the safety profile is covered. The description adds real value beyond that: it discloses the irreversible third-party side effect ('cannot be recalled') and the hidden state mutation (approving/opening a draft), which the annotations alone do not convey.

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?

Two tight sentences with the core action front-loaded and the critical irreversibility warning placed last for emphasis. No filler or restatement of the title.

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 destructive, open-world mutation with no output schema, the description covers the action, the required pre-existing draft, and the non-recallable consequence. It leaves the required permissions and the result of a dry_run unstated, but annotations and schema carry the rest adequately.

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 all five parameters (dry_run, idempotency_key, notify_supplier, supplier_message, purchase_order) are already documented. The description adds only a marginal hint ('e.g. by email') and does not elaborate on parameter behavior, so the baseline 3 is appropriate.

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 (Submits) and resource (one purchase order) plus its destination (to its supplier). It is clearly distinguishable from the sibling create_purchase_order and get_purchase_order_details, which operate on the draft/reference rather than sending it out.

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?

Implies usage by stating it acts on an existing PO ('approving and opening a draft first'), which tells the agent a draft must exist. However, it never explicitly says when to use this versus alternatives like create_purchase_order or record_purchase_invoice, leaving routing to inference.

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