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

Beyond the idempotent and destructive annotations, the description details exact side effects: accept grants credit plus a durable receipt, refuse grants no credit and preserves buyer redirect capability, and dispute-frozen purchases behave differently. It also discloses permanence consequences, buyer privacy, and the fact that buyer claim tokens should not be passed. No statement contradicts the annotations.

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?

The core operation and its main trade-off are front-loaded in the first sentences, and the edge-case behavior is grouped logically. The description is long and includes some optional navigation and founder-route lore, but most of the detail is directly relevant to safe invocation.

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?

Given two parameters, no output schema, and a moderately complex dispute/resolution state machine, the description covers the full decision space: which gifts qualify, what each action does, retry safety, frozen-state exceptions, private buyer information, and relevant external routes. An agent has enough information to select the correct action and avoid supplying invalid tokens.

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?

The action enum values are given real semantic content: accept means whole-dollar credit plus receipt, refuse means no credit and usually a redirectable purchase. The gift_id provenance is reinforced via me.city_fee_credit.pending_gifts, and the warning that no buyer claim token belongs in this tool is a useful guard. With only 50% schema description coverage, this compensation is adequate but not exhaustive.

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 opens with a specific verb ('Act on') and a specific resource ('prepaid fee-credit gift') and narrows the scope to gifts surfaced in me.city_fee_credit.pending_gifts. It clearly distinguishes accept from refuse by stating their respective effects, which separates this tool from the surrounding billing/lifecycle siblings.

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?

The description provides an explicit trigger condition: use the tool when the me endpoint has pointed to city_fee_credit.pending_gifts. It also describes the dispute-frozen state where accept becomes a no-op while refusal is still available. It does not name direct alternative tools or explicitly state when not to use this tool, so it stops short of a perfect usage guide.

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