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

The description adds significant behavioral context beyond the annotations: it warns that it only counts refusals where cost was declared, so it under-reports; it clarifies the dependency on estimated_cost_micros; and it explicitly states 'This is money not spent at your vendors, never money paid to Ratchet,' preventing misinterpretation of the metric. These are valuable transparency points that go well beyond the readOnly/idempotent hints.

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 compact (two main sentences plus an IMPORTANT note) and front-loads the core purpose. The key caveat about under-reporting is placed early, and the note about the dependency is clearly highlighted. No wasted words; every sentence earns its place.

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 read-only reporting tool with no parameters and no output schema, the description covers the essential aspects: what it does, how it behaves (under-reports), what it depends on, and what the number means. There is no missing information that an agent would need to call it correctly. The absence of an output schema is acceptable per guidelines since it isn't required to explain return values.

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 has zero parameters, so schema coverage is trivially 100%. No parameter explanation is needed. The description does reference a parameter on another tool (estimated_cost_micros) but that is not a parameter of this tool. Given the baseline of 4 for no-parameter tools, this score is appropriate.

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 states a specific action and resource: 'Counts duplicate actions refused in the last 30 days and what they would have cost.' This is a precise verb+resource definition that clearly distinguishes the tool from its siblings (e.g., ratchet_list_effects, ratchet_usage) by focusing on prevented financial loss. It also clarifies the metric's scope, making it easy to understand at a glance.

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 provides a critical prerequisite ('pass estimated_cost_micros on ratchet_begin_effect or this reads zero'), which helps the caller ensure meaningful output. However, it does not explicitly compare this tool to alternatives among the ratchet_* siblings or state when to prefer this over others. The guidance is more about operational dependency than tool selection, so it falls short of a 4.

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