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

Despite readOnlyHint and openWorldHint false already being present, the description adds substantial behavioral context: it reveals the data is real, describes the mode selection mechanism, details the exact return fields, mentions trend accumulation, and includes a disclaimer ('Analytical, not advice'). No contradictions 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 a dense but well-organized paragraph. Every sentence adds value, but it could be slightly more structured with bullets or shorter sentences. The '[DRILL-DOWN]' prefix and disclaimer are useful, though the text feels a bit overloaded.

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?

Without an output schema, the description thoroughly explains return values: latest buckets, totals, long_pct, ls_ratio, trend, and context fields. It also references the REST endpoint and data sources, covering all necessary aspects for a 2-parameter tool. The tool's complexity is well addressed.

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?

With 0% schema coverage, the description fully compensates by explaining both parameters: 'coin' is the asset whose positioning is returned, and 'days' is the trend window with range (1-90) and default (7). This goes beyond the bare schema definitions.

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 clearly states the tool returns long/short positioning for a single coin, with specific data elements and source modes. It distinguishes itself from the sibling get_positioning by framing itself as the raw 'who-is-long-where' view, making the purpose unmistakable.

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 names get_positioning as a complement, telling the user when this tool is appropriate (for raw data vs. the 8-leg synthesis). It also explains the source selection logic based on asset type, providing clear context for when to use this tool.

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