checkout_cancelCancel an in-progress checkout session. Releases any held inventory and cancels the associated Stripe PaymentIntent if not yet captured. Requires authentication.
| Name | Required | Description | Default |
|---|---|---|---|
| checkout_id | Yes | Checkout session ID to cancel | |
| bearer_token | No | Authentication token for the patient session |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite annotations already indicating destructive and non-read-only behavior, the description adds critical detail: it releases held inventory and cancels the associated Stripe PaymentIntent if not yet captured. This goes beyond the annotations and explains what happens, including a conditional aspect. No contradiction exists.
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 with no filler. The first sentence states the core action, and the second covers additional effects and authentication. All information is relevant and front-loaded.
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 output schema exists and annotations cover safety, the description is largely complete for a cancellation tool. It covers purpose, effects, and authentication. Minor gaps like error conditions or prerequisites are not mentioned, but they are not essential for this tool's complexity.
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 100%, so the parameters are already well-documented by the schema. The description does not add extra semantics beyond referencing 'checkout session' in the text, which aligns with the schema's checkout_id description. Baseline 3 is appropriate.
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 ('Cancel') and resource ('in-progress checkout session'), clearly distinguishing it from sibling tools like checkout_create, checkout_complete, and checkout_status. It also adds scope ('in-progress') and key effects (releases inventory, cancels Stripe PaymentIntent), making the purpose unmistakable.
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 phrase 'in-progress checkout session' provides clear context for when to use this tool, implying that it is for sessions not yet completed. However, it does not explicitly state when not to use it or name alternatives (e.g., use checkout_complete to finish), so it lacks explicit exclusions.
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.
Most tools have distinct purposes with clear boundaries, such as auth_* for authentication, checkout_* for payment, and portal_* for patient portal actions. However, there is some overlap between checkout_status and auth_check_payment (both involve polling for payment status) and between portal_support and portal_message (both for communication), which could cause minor confusion.
Tool names follow a highly consistent verb_noun pattern throughout, with clear prefixes grouping related tools (e.g., auth_, checkout_, consent_, intake_, medications_, order_, portal_, provider_). This predictable structure makes it easy to understand the tool set's organization and purpose.
With 34 tools, the count is borderline high for a telehealth server, as it may feel heavy and complex for agents to navigate. While the tools cover a comprehensive workflow from authentication to patient portal, some consolidation (e.g., merging similar polling tools) could improve usability without losing functionality.
The tool set provides complete coverage for the telehealth domain, including authentication, eligibility checks, medication browsing, intake, consent, checkout, order management, and patient portal features. There are no obvious gaps; agents can handle the entire patient journey from start to ongoing care without dead ends.