Destructive financial operations in Feegow. Actions:
remove_invoice: remove an invoice.
remove_payment: remove a payment.
cancel_voucher: cancel a voucher. All are irreversible.
[Flattened action: cancel_voucher]
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | ||
| account | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already include destructiveHint=true, indicating irreversibility. The description adds 'All are irreversible,' which reinforces but doesn't substantially expand beyond the annotation. The mention of unrelated actions introduces slight confusion, but there is no contradiction with 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 description is relatively short but includes extraneous listing of other actions not relevant to this specific tool. The flattened action note is helpful. Some noise could be removed without losing meaning.
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?
With no output schema and minimal description, the tool lacks information on return values, error conditions, or side effects beyond irreversibility. For a destructive operation, more context (e.g., what happens to related data) is needed for safe use.
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 coverage is 0%, and the description provides no explanation of the parameters 'data' and 'account'. The agent must infer their purpose (likely voucher identifier and account context) without any guidance, risking misuse.
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 the tool cancels a voucher, with a clear flattened action. However, it also lists other actions (remove_invoice, remove_payment) that belong to sibling tools, causing minor confusion. The resource and operation are clear, but differentiation from similar tools is not explicit.
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 warns that operations are irreversible but provides no guidance on when to use this tool versus sibling delete tools (e.g., feegow_financial_delete_remove_invoice). No context on prerequisites or appropriate scenarios is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Many tools have identical descriptions (e.g., multiple tools with same 'Read appointments and scheduling data' text) and only differ by a 'flattened action' label, making it impossible for an agent to distinguish which tool to call for a specific operation.
Names follow a loose verb_noun pattern but are extremely inconsistent: some use underscores, some have redundant prefixes like 'feegow_appointment_', and the same actions are duplicated across multiple tool names (e.g., 'list' appears in many). The 'flattened action' suffix is confusing.
94 tools is far too many for a clinic management system. This is clearly due to a one-action-per-tool design that fragments the API surface, making the server bloated and hard to navigate. A typical well-structured server for this domain would have 10-20 tools.
The server covers many areas (appointments, patients, financial, procedures, stock, etc.), suggesting broad functionality. However, the fragmentation obscures gaps and makes it difficult to determine if all CRUD operations exist for each entity. Some areas (e.g., stock write) have multiple tools for single actions.