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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, and the description adds important non-obvious behavior: the linkage is best-effort temporal matching, not a foreign key; paper trading only; a standard disclaimer per page; and pagination requires following next_cursor until has_more=false. 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 structured with clear labels (Purpose, Triggers, When to call, etc.) and stays on-topic, but the detailed 'Output:' block overlaps with the existing output schema, adding length. Still, every section contributes operational guidance, so the redundancy is mild.

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 paginated bulk export with temporal-linkage caveats, the description covers purpose, triggers, parameter limits, pagination mechanics, linkage fidelity, disclaimer behavior, and a next-step cross-check. Output schema exists, but the description still provides enough context for safe offline use.

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 carry parameter semantics. The Args section explains market values, cursor semantics as 'last trade id from previous page (0 = start)', limit max 500, and days as exit-time window max 120 — going well beyond the bare schema defaults.

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 phrase 'Cursor-paginated bulk export of the prediction -> trade -> outcome chain' and names paper trades with realized P&L, making it distinct from siblings like get_trade_history and get_resolved_predictions. It explicitly says it is for pipeline consumers, not conversational snippets.

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?

It provides explicit trigger phrases, a 'When to call' list (offline verification, periodic ingestion, auditing), and a direct alternative for the prediction ledger via get_resolved_predictions. It also excludes conversational use by saying 'not conversational snippets.'

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