Get Cursor usage + conserve decision

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Given the absence of annotations, the description discloses key behavioral traits: automatic authentication via Cursor's local token, handling of needsLogin, and caching behavior with refresh support. This gives the agent comprehensive insight beyond the tool's name and schema.

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 well-structured and front-loaded with the call timing instruction, followed by purpose and actionable conditional logic. Each sentence provides necessary information without redundancy, making it appropriately sized for the tool's complexity.

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 tool has no output schema, so the description compensates by explaining the return flags (conserve, followup, needsLogin) and how to respond to each. It also covers auth and caching behaviors, making it complete enough for an agent to invoke correctly.

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 schema already describes the refresh parameter as bypassing the cache, and the description adds valuable context about when caching is active (once quota is exhausted until cycle resets) and why refresh would be needed. This enriches the parameter's meaning and improves correct usage.

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 states the tool's function: reading the user's current Cursor usage/spend and returning conserve and followup flags. This distinguishes it from siblings like usage_breakdown, which likely provides detailed breakdowns, by focusing on the summary decision flags.

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 explicitly instructs to call this at the START of a task and provides conditional behavior based on the returned flags (e.g., using the questions/options UI when conserve is true, ending with an options question when followup is true). However, it does not explicitly mention alternatives or when not to use it beyond those conditions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.