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

Annotations declare readOnlyHint, idempotentHint, and openWorldHint, which already cover the safety profile. The description adds meaningful behavioral context beyond these: cursor pagination details, the audit/evidence role (e.g., 'AI agents can snapshot open predictions, wait, then verify outcomes themselves without trusting our DB'), and a paper-research disclaimer. It does not contradict annotations and provides useful caveats about pagination and non-investment nature.

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 organized with clear labeled sections (Purpose, Triggers, When to call, Prerequisites, Next steps, Caveats, Output, Args, Disclaimer). Every section adds value — triggers help routing, caveats prevent misuse, and output formatting aids parsing. It is longer than average but each sentence earns its place; the structure is front-loaded with the essential purpose.

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 6-parameter tool with an output schema, the description is remarkably complete. It covers output structure (full_data with predictions[], count, next_cursor, has_more, meta), pagination semantics, filter usage, relationships to sibling tools, and the audit context. No important behavioral or usage aspect is left unexplained; the agent has everything needed to select and invoke the tool 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?

The 'Args' section goes well beyond the bare schema: it explains each parameter with concrete examples (e.g., target_market values 'coin_market'/'kr_market'/'us_market', source_category 'vix'/'bonds'/'commodities'), clarifies day as UTC and a string prefix of created_at, defines status values, and specifies cursor as last id and limit max 500. This fully compensates for the 0% schema description coverage and makes parameter usage unambiguous.

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?

Description opens with a specific and vivid purpose: 'Raw, row-level prediction ledger — every macro regime prediction's full lifecycle (created_at -> resolved_at -> outcome).' This clearly distinguishes it from sibling tools like get_prediction_accuracy (aggregates) and get_active_predictions (likely active only). The verbal resource and scope are explicit.

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?

Provides explicit 'When to call' guidance: credibility evaluation, independent backtesting, archiving. It also mentions pairing with get_ledger_integrity and next steps. However, it lacks an explicit 'when not to use' / exclusion statement; the alternative tool (get_prediction_accuracy) is implied but not explicitly contrasted as 'use this for summaries.' The triggers and prerequisites are strong, but the absence of a clear negative case costs a point.

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