get_usageThe caller's quota position: tool calls used today and in the last minute, the limits, and when they reset. Does not count against the daily quota (each request still uses one per-minute slot).
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
| Name | Required | Description | Default |
|---|---|---|---|
| day | Yes | ||
| tier | No | This account's tier; present only while more than one is offered. | |
| minute | Yes |
Changes observed during successful MCP inspections.
Output schema / properties / tier / descriptionPrevious value: -"This account's tier."New value: +"This account's tier; present only while more than one is offered."Output schema / requiredPrevious value: -[
- "tier",
- "day",
- "minute"
-]New value: +[
+ "day",
+ "minute"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes beyond the readOnly/non-destructive annotations by disclosing a real side effect the structured fields don't capture: the request does not count against the daily quota but does consume one per-minute slot. That is precisely the behavioral detail an agent needs to decide whether it can poll.
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, zero waste. Return content comes first, the quota/cost caveat second – front-loaded and easy to scan.
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 parameterless read-only tool with an output schema, everything needed is present: what is returned, that the schema covers the shape, and the quota accounting rule. Nothing required for correct invocation is missing.
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?
The tool takes zero parameters, so the baseline is 4; there is no parameter semantics to obscure and the description correctly implies no input is needed.
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 and resource (the caller's quota position) and enumerates exactly what is reported: tool calls used today, in the last minute, the limits, and reset timing. An agent can tell precisely what it will get back without opening the output schema.
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?
Explains the cost model of calling it – free against the daily quota but consuming a per-minute slot – which tells an agent it is cheap to check before making other calls. It stops short of stating an explicit when-to-call trigger (e.g. 'call before retrying after a limit error'), and no alternative tool exists to route to.
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.