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

With no annotations, the description still discloses the key behavioral traits of this mutation: job cost is left intact and the line becomes receivable again, so the agent knows the effect is a reversible state rollback. Authorization scope ('Owner or office') is also surfaced. It does not say what happens to any recorded bill or stock quantities, which is the remaining gap.

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?

Three short sentences, front-loaded with the action and its effect, with the permission note last. Nothing is padded or repeated from 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?

An output schema exists, so return values need not be explained, and the core reversal semantics are covered. However, for an unannotated mutation with 0% parameter coverage, the definition should identify the required material_id and explain the free-text reason; it also leaves downstream effects on bills/stock implicit.

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% for two parameters, so the description must carry the load — but it never mentions material_id or the optional reason (max 500 chars). 'A received material' only loosely implies a material identifier, and the reason field is completely undocumented.

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 ('take back') and resource ('a received material from a purchase order'), which clearly positions it as the inverse of po_receive rather than po_cancel or po_update. Sibling names are not cited explicitly, but the reversal semantics are unambiguous.

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 concrete triggering conditions — 'wrong part, returned' — and a permission note ('Owner or office'). It does not contrast with po_cancel (whole-order cancellation) or state when undo is disallowed, so no explicit exclusions.

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