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

With no annotations, the description carries the disclosure burden and does so well on the two highest-risk points: lines are a full replacement ('lines replace all lines'), and the caller must be owner or office. It omits failure behavior for non-draft POs and whether omitted fields (note/vendor/lines) are left untouched.

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?

A single sentence with no filler, front-loading the mutation target and parenthesizing the one non-obvious destructive detail. Every clause carries 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?

An output schema exists, so return values need not be explained, and the tool is a simple 4-parameter mutation. The draft-only precondition, replace-all lines semantics, and authorization are covered; the remaining gap is the non-draft error path and partial-update behavior.

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 0%, so the description must compensate; it does partially by mapping 'supplier' to vendor_id and flagging the replace-all semantics of lines, which the schema cannot express. It says nothing about the line object's own fields (quantity, unit_cost_minor, unit_price_minor) or the uuid format of po_id/vendor_id.

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 ('Change') plus resource ('draft purchase order') and enumerates the mutable fields (supplier, note, lines). The 'draft' scope alone separates it from sibling operations like po_markOrdered, po_receive, or po_cancel that act on non-draft POs.

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?

'draft purchase order' implies the pre-ordered state is a precondition, and 'Owner or office' signals who may call it. But there is no explicit statement of what to do for a non-draft PO (e.g., whether to cancel and recreate) and no named alternative among the many po_* siblings.

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