llm_savings

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

As a read-only reporting tool, the description accurately conveys it 'displays' and 'returns' data without side effects. With no annotations provided, this is sufficient transparency, though it could explicitly state 'read-only' or note that no data modification occurs.

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 three sentences, front-loaded with the core purpose, then details, then output note. Every sentence is essential and there is no fluff, making it highly concise and clear.

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 zero-parameter tool with an output schema, the description covers the key output and context (real dollar value of routing). It could add brief guidance on when to choose this over similar tools, but overall it is sufficiently complete.

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 input schema has zero parameters, and the description adds meaning by explaining the output fields (actual spend, baseline, multiplier). It also implies that all time periods are returned, which is consistent with the empty schema, providing value beyond the schema itself.

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 shows a time-bucketed savings dashboard with specific periods (today, this week, this month, all-time) and metrics (spend vs Sonnet baseline, efficiency multiplier). This distinct purpose separates it from siblings like llm_usage or llm_dashboard, which focus on raw usage or general dashboards.

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 says 'Use this to understand the real dollar value routing provides,' providing a clear use case. However, it doesn't mention when not to use it or contrast with alternatives like llm_budget or llm_session_spend, which slightly reduces guidance completeness.

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