Retrieve persisted token usage and estimated CNY costs, with optional filters by model or ISO-8601 time range, to monitor AI model consumption and spending.
Get persisted token usage and estimated CNY cost, optionally filtered by model or time range.
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | ||
| since | No | ISO-8601 timestamp | |
| until | No | ISO-8601 timestamp |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. 'Get' implies a read, 'persisted' signals stored (not live) data, and 'estimated' discloses that the CNY cost is approximate — meaningful behavioral nuance. It does not state scope (per-user/session/global), aggregation granularity, or permissions.
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?
A single front-loaded sentence with no filler; the core action, return content, and optional filters all appear before any padding.
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?
For a simple three-optional-param read tool with no output schema, the description names what is returned (token usage plus estimated cost) and how it can be narrowed. Minor gaps remain around result scope and aggregation granularity, but nothing blocks correct invocation.
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 67% ('model' is undocumented; 'since'/'until' carry ISO-8601 notes). The description maps the three params to 'filtered by model or time range', adding a semantic grouping but no format or default details beyond the 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?
States a specific verb ('Get') and a precise resource ('persisted token usage and estimated CNY cost'), which is unambiguous. The sibling tools are all task-routing/status operations, so no explicit differentiation is needed, though none is offered.
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?
'optionally filtered by model or time range' implies the filtering use case but gives no when-to-use or when-not-to-use guidance. Because no sibling covers usage reporting, the lack of alternatives is less costly, but the description still leaves invocation conditions implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.