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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint. The description adds valuable context beyond those: it states the tool returns specific fields per event type, and provides a caveat ('empty when no news events processed in the recent window'). This is meaningful behavioral disclosure, though it doesn't mention performance or rate limits, so a 4 is appropriate.

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 well-structured with labeled sections (Purpose, Triggers, When to call, Prerequisites, Next steps, Caveats, Args, Disclaimer) and front-loads the core purpose. It is slightly verbose with multiple trigger examples and Trust Layer context, but every section earns its place for a developer-facing tool.

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?

The description is comprehensive given the tool's simplicity and available structure. It covers purpose, usage triggers, prerequisites, caveats, parameter meanings, next steps, and a disclaimer. The output schema exists, so return values are further specified elsewhere. There are no significant gaps for a read-only retrieval tool.

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 input schema has 0% description coverage, but the description compensates fully with an 'Args' section that explains each parameter: market_id ('Market identifier (crypto, kr_stock, us_stock, etc.)'), target_market ('Alias for market_id (backward compat)'), and min_sample_count ('Minimum sample count for statistical significance (default 3)'). This adds clear meaning beyond the bare schema.

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 and resource: 'Evidence that OneQAZ detects price moves BEFORE news publication. Returns leading_score, avg_lead_time_minutes, and accuracy_pct per event type.' It clearly states what the tool does and differentiates from siblings by mentioning 'Trust Layer A evidence' and pointing to get_news_causality_breakdown as a next step, avoiding confusion with other news-related 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?

Includes explicit trigger examples ('can you predict news?', 'how early do you catch moves?'), a dedicated 'When to call' condition ('when an AI is evaluating predictive capability'), prerequisites ('none'), and a 'Next steps' alternative (get_news_causality_breakdown). This meets the 5-level bar for when/how to use and alternatives.

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