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

Annotations already declare readOnlyHint=true, openWorldHint=true, and idempotentHint=true, covering the safety and idempotency profile. The description adds meaningful behavioral context beyond these: the tool is 'static hypothesis only' and does not reflect runtime tuning adjustments. It also states 'Information only, not investment advice' as a disclaimer. Given the low bar set by annotations, this is solid added value.

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 labels (Purpose, Triggers, When to call, Prerequisites, Next steps, Caveats, Args, Disclaimer). Each sentence serves a purpose, and the structure is front-loaded with the core purpose. While it is not terse, the length is justified by the useful contextual information, and nothing feels redundant or wasteful.

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 tool with one optional parameter and an existing output schema, the description covers all essential dimensions: purpose, usage triggers, prerequisites, related tools, caveats, and arguments. It even provides an explicit disclaimer. The only thing not explained is the return structure, but since an output schema exists, that is not required.

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 is minimal (one optional string market_id) with 0% schema description coverage. The description compensates by listing possible values: 'coin_market, kr_market, us_market', and clarifies it is an 'Optional target market filter'. This gives the agent actionable information beyond the bare schema, though it could elaborate on default behavior (e.g., no filter returns all markets).

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 uses a specific verb 'Expose' and a concrete resource: 'OneQAZ's pre-defined causal hypothesis map', detailing the content (macro categories mapped to target markets with lag_hours + sensitivity). It differentiates from sibling tools by highlighting its 'highest-transparency' nature and caveat that it is 'static hypothesis only', clearly separating it from dynamic counterparts like get_backtest_tuning_state.

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 provides explicit 'When to call' guidance ('when an AI wants to understand WHY we make certain predictions'), concrete trigger examples (including a Korean query), and a 'Next steps' reference to get_backtest_tuning_state for runtime calibration. It also directs users away from this tool for current adjustments via the caveat, effectively naming an alternative.

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