Get Study Prediction Access

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior, and the description adds substantial value beyond them: it confirms the absence of side effects, discloses coverage blind spots, and provides interpretive caveats about what the data can and cannot prove. No contradiction with annotations.

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?

Four short sentences, each earning its place: core purpose, negative behavior, coverage limits, and interpretation caveat. The most important information is front-loaded and there is zero redundancy or filler.

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 compliance-relevant read tool with rich annotations and an output schema present, the description is remarkably complete. It covers the critical interpretive pitfalls (absence of history doesn't prove holdout untouched; repeated access doesn't prove retuning) which is exactly the context an agent needs. Return structure is covered by the output schema.

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 coverage is 0%, so the description must compensate. It does so by clarifying that run_id identifies 'this run' and that the access history is scoped to the run plus matching recorded dataset/windows in the study. It doesn't detail the run_id format, but for a single obviously-named required parameter this is adequate compensation.

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 ('Read'), a specific resource ('partial prediction-access history'), and precise scope ('for this run and matching recorded dataset/windows in this study'). It also distinguishes itself from siblings by stating what it does not do ('Does not expose predictions or add access events'), differentiating it from tools like declare_study_holdout_use.

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 gives clear context about what the tool covers and, importantly, what it does not cover ('Earlier activity, other result routes and offline work are not covered'). It implies when not to rely on it ('absence never proves untouched holdout status'), but it does not explicitly name alternative tools or state direct when-to-use conditions.

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