llm_update_usage

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

No annotations are provided, so the description carries the full burden. It explains that the tool updates cached data and its downstream use, but does not disclose potential side effects, permissions, or error behavior. A middle score is appropriate.

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 reasonably concise, starting with a clear purpose. The bullet point and additional context are helpful, though some sentences could be more tightly integrated. Still efficient overall.

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?

Given the presence of an output schema, the description adequately covers input, usage context, and relationship to other tools (llm_classify). It explains the significance of the cached data for budget pressure, making the tool's role clear.

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?

With 0% schema description coverage, the description adds significant meaning to the single parameter 'data' by specifying it should be the JSON response from the claude.ai usage API. Without this, the schema only declares an object type.

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 verb 'Update' and the resource 'cached Claude usage', and specifies that it accepts the result from browser_evaluate(FETCH_USAGE_JS), distinguishing it from sibling tools like llm_check_usage and llm_track_usage.

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?

Explicitly instructs to call this with the result from browser_evaluate(FETCH_USAGE_JS) and that it accepts the full JSON object from the claude.ai internal API. Also explains that cached data is used by llm_classify for budget pressure, providing clear context for when to use.

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