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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds valuable behavioral context: unscored rows are excluded (never counted as zero), there is deliberately no combined figure, and skill is measured against the track's own base rate inside the window. This goes beyond the annotations and helps the agent interpret results correctly.

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 moderately sized but information-dense. It front-loads the core purpose and then provides essential behavioral details. Every sentence earns its place, though the window_days explanation is somewhat long and could be tightened. Still, it is well-structured and not bloated.

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 tool's moderate complexity (3 optional params, no output schema), the description covers the key aspects: what is returned, how tracks are separated, how scoring works, and how to interpret the window. The only minor gap is that it doesn't explicitly describe the reply structure beyond pct_scored_last_7d, but the description is otherwise complete enough for an agent to call it correctly.

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%, so the schema already documents all three parameters. The description adds meaning by explaining the track semantics (house, machine, creator) and the window_days nuance (90d is the shortest window with house evidence, and the yardstick is computed inside the window). This adds value beyond the schema's enum and type definitions.

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 verb ('query') and resource ('eYKON's own forecast record'), and clearly distinguishes this tool from siblings by naming the three tracks (house, machine, creator) and the metrics (Brier and log-loss per track). It also explicitly notes that tracks never blend, which differentiates it from other query tools.

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 explicit guidance on when to use this tool: it is for eYKON's own forecast record, and it explains the track semantics. It also gives practical usage advice, such as checking pct_scored_last_7d to determine if the window bound, and notes that 90 days is the shortest window with house-track evidence. This is strong contextual guidance.

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