orb_get_customer_costsGet costs incurred by a customer over a timeframe. Orb API: GET /customers/{customer_id}/costs.
| Name | Required | Description | Default |
|---|---|---|---|
| group_by | No | Price grouping key to break costs down by. | |
| view_mode | No | periodic or cumulative. | |
| customer_id | Yes | Orb customer id. | |
| timeframe_end | No | ISO-8601 datetime, exclusive end. | |
| timeframe_start | No | ISO-8601 datetime, inclusive start. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the description does not need to establish the safety profile. It adds the timeframe scope and API endpoint but does not describe output shape, pagination, defaults, or how group_by and view_mode affect results. There is no contradiction, but behavioral detail is thin.
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 concise and front-loaded, with the core operation in the first sentence. The second sentence names the Orb API endpoint, which is useful reference but not essential for selecting or invoking the MCP tool.
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?
The schema fully documents the parameters and the readOnly annotation covers safety, so a basic call can be made. However, with no output schema, the description does not explain what the returned cost data looks like, and it does not distinguish this from subscription-level costs, leaving moderate ambiguity.
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%: every parameter has a meaningful description, so the tool description does not need to compensate. The description adds no parameter details beyond the schema, so the high-coverage baseline of 3 applies.
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 a specific verb and resource: get costs incurred by a customer, with a timeframe constraint. It is clear, but it does not explicitly distinguish itself from the sibling orb_get_subscription_costs, so it does not earn the top score.
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?
There is no guidance on when to use this tool versus alternatives such as orb_get_subscription_costs or orb_get_customer_credits. The timeframe phrase is part of the operation, not a usage condition, and no exclusions or alternatives are mentioned.
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.
Every tool name clearly specifies a distinct action and resource (e.g., list_subscriptions vs get_subscription). There is no ambiguity between tools as each targets a unique combination of verb and noun.
All tool names follow a consistent pattern: 'orb_<verb>_<resource>' in snake_case. This makes them predictable and easy to distinguish.
With 26 tools, the set covers many resources and operations for a billing platform. While slightly above typical range, each tool justifies its existence given the domain complexity.
The tool surface provides extensive read capabilities and basic customer CRUD, but lacks create/update/delete for most other resources (e.g., subscriptions, invoices) and missing operations like void or cancel. This creates notable gaps for full lifecycle management.