Get Study Prediction Access

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

The description goes well beyond the annotations. It discloses that the read does not expose predictions or add events, that listing assessments never records, that histories before jellyfish #837 may contain extra rows, and that nothing is deleted because holdout-use declarations reference event ids. These are critical behavioral traits not captured by readOnlyHint/openWorldHint/idempotentHint/destructiveHint. 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?

The description is dense but every sentence earns its place. It front-loads the core purpose and return fields, then adds necessary caveats about event recording, historical anomalies, and limitations. It is longer than average, but the complexity of the tool justifies the length. Slight redundancy in the caveats could be trimmed, but overall it is well-structured.

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 complexity, the single parameter, the rich annotations, and the presence of an output schema, the description is complete. It explains what is returned, what is not covered, how events are recorded, and the implications for holdout status. An agent has everything needed to decide when to call this tool and how to interpret its results.

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 for the single parameter run_id. The description repeatedly references 'this run' and 'matching recorded dataset/windows in this study', implying run_id identifies the run, but it does not explicitly state that run_id is the run identifier or explain its format. However, with only one parameter and the title 'Run Id' in the schema, the meaning is largely inferable. Baseline 3 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 verb ('Read') and resource ('partial prediction-access history for this run and matching recorded dataset/windows in this study'), and enumerates the exact fields returned. It clearly distinguishes itself from sibling tools by focusing on prediction-access history rather than study metadata, runs, or models.

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 explains when this tool is appropriate: to read prediction-access history for a run and its recorded dataset/windows. It also provides exclusions ('Earlier activity, other result routes and offline work are not covered; absence never proves untouched holdout status. Repeated access does not prove retuning.'), which tells an agent when NOT to rely on this tool. This is strong usage guidance.

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