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

Annotations already declare non-read-only, non-destructive, and idempotent behavior, so the bar is lower. The description adds real value beyond them: it discloses the state effect ("The rebate returns to the buyer's balance") and the timing boundary (before payment starts), which an agent needs to reason about consequences.

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 sentences, zero waste, and the action and its condition are front-loaded. Every sentence 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?

For a non-destructive mutation with annotation coverage and no output schema, the description covers purpose, timing, and effect. It still omits why confirm=true is mandatory (a safety gate an agent should understand) and provides no error or failure conditions, which matters for a required-confirm mutation.

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% across 3 required parameters. The description only weakly implies order_id via "this order's rebate" and says nothing about the confirm gate (const true) or the idempotency_key, leaving two of three parameters unexplained by either schema or prose.

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?

The description uses a specific verb ("Withdraw") on a specific resource ("this order's rebate choice") and scopes it temporally ("before payment starts"). It clearly distinguishes itself from evuun_apply_rebate in spirit, though it never names the sibling or states the inverse relationship explicitly.

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?

"Before payment starts" is a genuine usage precondition that tells an agent when this tool is valid. However, there is no explicit guidance on alternatives (e.g., evuun_apply_rebate to choose a different rebate, or evuun_get_rebates to inspect before withdrawing), so the routing is only implied.

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