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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the agent knows it is safe and repeatable. The description adds meaningful behavioral context: each row compares a prior run's projection against actuals, and it explains how to interpret the output (trends, optimism bias). It goes beyond a simple 'returns data' statement.

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?

Two sentences, purpose first, no fluff. The first sentence states the core functionality, the second provides use-case context. Every word 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?

Given the simplicity (one parameter, output schema present), the description covers the essential context: what is returned, how to interpret it, and why the tool might be used. It does not mention edge cases like empty runs, but the output schema likely covers response shape. This is a well-rounded description for a focused tool.

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 0%, so the description must compensate. Although forecast_id is not explicitly defined, the description repeatedly refers to 'a forecast' and 'your forecasts', making it clear that forecast_id identifies the relevant forecast. With only one parameter, the semantics are effectively conveyed.

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 opens with a specific verb+resource: 'Returns per-past-run accuracy for a forecast.' This clearly distinguishes it from sibling tools like get_forecast (forecast details) and get_forecast_run (single run details). The purpose is immediately understandable.

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 states when to use the tool: 'Use this to see whether your forecasts have been getting MORE or LESS accurate over time, or to spot when a backtest sMAPE was systematically optimistic.' While it does not name alternative tools explicitly, the context is clear and actionable.

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