square_create_refund

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

With no annotations provided, the description carries the full burden. It mentions routing and authentication scope but fails to disclose behavioral traits like whether the refund is synchronous, if it modifies state, or any required permissions. This is insufficient for a mutation tool.

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 very short and to the point, but it omits critical information. It is concise at the expense of completeness.

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 the tool creates a refund and has an output schema (not shown), the description is incomplete. It does not explain what arguments to provide, what the output contains, or any side effects. A mutation tool without usage details is inadequate.

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 schema has a single 'arguments' parameter with 0% description coverage. The description only states it is a 'JSON string of arguments for the connector operation' without detailing expected keys (e.g., payment_id, amount). This adds almost no semantic value.

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 states 'Square connector operation create_refund' which clearly identifies the verb (create) and resource (refund). However, it lacks specificity about what a refund entails (e.g., refunding a payment) and does not distinguish it from similar tools like stripe_create_refund or square_list_refunds.

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 no guidance on when to use this tool, such as prerequisites (e.g., needing a payment ID) or when not to use it. No comparisons with sibling tools are offered.

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