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

Annotations already declare readOnlyHint=true, and the description adds context by specifying exactly what metrics are included and the notable exclusion of LLM cost. This goes beyond the annotation to set expectations about the data content, though it doesn't address rate limits or auth requirements.

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?

Three concise sentences front-load the purpose, then detail outputs, and end with a clarifying caveat. No redundant or filler content—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 simple read-only usage tool with two optional params and no output schema, the description sufficiently explains what data the user will receive. However, it could be more complete by clarifying how 'grading runs' factor into usage or how cost is calculated, though these are not critical gaps.

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?

Schema description coverage is 100% for both parameters (year_month and include_history), so the description doesn't need to repeat them. The description adds no extra detail beyond the schema, earning the baseline score of 3.

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 ('Get token usage and cost metrics') and lists the concrete outputs (input/output tokens, cost, grading runs, per-agent breakdown). It clearly distinguishes this from sibling tools like grading result or session list tools by focusing on usage and cost data.

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 implies the tool is for accessing usage/cost metrics and clarifies it does not include LLM costs, providing context for when it's appropriate. However, it does not explicitly contrast with alternative tools or state when not to use it, so it falls short of a full 5.

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