Meter receipts, two shapes. Day: agentId + day — the operator-ratified grant with its provider report. Ledger: any since/until/limit/cursor argument lists run-id receipts by mint time (limit 1-30, default 20; echo nextCursor verbatim), agentId/day filters optional.
| Name | Required | Description | Default |
|---|---|---|---|
| day | No | ||
| limit | No | ||
| since | No | ||
| until | No | ||
| cursor | No | Opaque server-minted cursor (<=256 chars); echo nextCursor verbatim with the same filters. | |
| agentId | No |
Changes observed during successful MCP inspections.
Input schema / properties / cursorAdded value: +{
+ "description": "Opaque server-minted cursor (<=256 chars); echo nextCursor verbatim with the same filters.",
+ "type": "string"
+}Input schema / properties / limitAdded value: +{
+ "maximum": 30,
+ "minimum": 1,
+ "type": "integer"
+}Input schema / properties / sinceAdded value: +{
+ "minimum": 0,
+ "type": "integer"
+}Input schema / properties / untilAdded value: +{
+ "minimum": 0,
+ "type": "integer"
+}Input schema / requiredRemoved value: -[
- "agentId",
- "day"
-]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden and does well: it discloses pagination defaults (limit 1-30, default 20), requires echoing nextCursor verbatim, and explains what each shape returns. It does not mention read-only status, authorization, or rate limits, but for a read-style tool the described behaviors are substantial.
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 compact and information-dense, organized into two labeled modes. Every sentence earns its place, and the structure makes the dual behavior easy to scan. It is slightly telegraphic, but this is a strong conciseness trade-off for the amount of behavior covered.
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 no annotations, the description explains both return shapes and key input behavior, covering pagination and filters. Gaps remain: since/until semantics are vague, 'run-id receipts' is not defined, and no error or authorization context is provided. Still, it is sufficiently complete for an agent to call the tool correctly in most cases.
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 only 17%, so the description must compensate, and it does: it explains the roles of agentId, day, since/until/limit/cursor, and adds constraints like limit range, default, and cursor handling. It could be more explicit about units/format for since/until, but overall it adds meaningful meaning beyond the sparse schema.
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 identifies the resource ('Meter receipts') and enumerates two distinct retrieval modes: daily (agentId + day) and ledger (since/until/limit/cursor). It is unambiguous about what the tool returns, though it does not explicitly state a verb such as 'get' or 'retrieve' and does not name sibling get_meter_receipt_run as a different tool.
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 concrete conditions for when to use each shape: day mode requires agentId + day, ledger mode is for list-style queries with pagination. It clarifies optional filters and default behavior, giving clear context. However, it does not explicitly compare against alternatives like get_meter_receipt_run or state when not to use this tool.
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.