freelance_refund_milestone

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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals that the tool moves money, requires the SPEND scope (enforced by the server), is reversible (funding restores it), carries no acknowledgement flag, and is a decision about someone's pay that should be confirmed before calling. This is rich, honest disclosure of side effects and prerequisites.

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 description is front-loaded with 'MOVES MONEY' and is concise at four sentences. It efficiently conveys purpose, prerequisites, reversibility, and a caution. The note about the acknowledgement flag is an internal detail but still relevant. No wasted words, though the aside about the flag could be seen as slightly extraneous; overall it is well-structured.

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 financial tool with two parameters and no output schema, the description covers the key operational aspects: what it does, the required scope, reversibility, and a warning to confirm. It does not detail return values, but that is not required without an output schema. The context is sufficient for an agent to decide when to call it and what to expect.

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?

Both parameters (id and milestoneId) are fully documented in the schema with descriptions ('The contract id' and 'The milestone id'), giving 100% coverage. The tool description adds no additional meaning about how these parameters are used or how they relate to the refund operation. Per the rubric, baseline 3 is appropriate when schema covers parameters fully and the description does not augment it.

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 clearly states the action: 'Take escrowed money back out of a milestone and return it to the organization's spendable balance'. This is a specific verb (refund) and resource (milestone), and the opening 'MOVES MONEY' signals a financial mutation. It also distinguishes itself from siblings by emphasizing the condition 'while nothing has been handed over', which differentiates it from approve_milestone or fund_milestone.

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 implies usage with 'while nothing has been handed over', indicating the tool is for refunding escrowed funds before delivery. However, it does not explicitly state when to use this tool versus alternatives like fund_milestone or approve_milestone, nor does it provide explicit 'use when / use instead' guidance. The condition is implied but not fully explicit.

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