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

Annotations already provide readOnlyHint=true, so the description doesn't need to restate safety. It adds valuable context: the mode is 'picked by the asset's primary source', indicating behavior varies by asset class. It also details what is returned (buckets, totals, long_pct, ls_ratio, funding, OI-by-venue) and that the accumulated trend over `days` is included, going beyond the schema. It could mention pagination or error cases but is otherwise solid, 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 a single, information-dense paragraph with a clear prefix, return value enumeration, and relationship to a sibling tool. It is front-loaded with the key purpose and is moderately concise for the amount of context it provides. It could be split into bullets or shorter sentences, but it earns its place.

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?

Given 2 simple parameters, readOnlyHint annotation, no output schema, and a rich description covering sources, return fields, day range, and sibling relationship, the description is largely complete. It omits an explicit return type shape but enumerates return contents. It is not a full 5 because it could briefly mention what happens for coins without a primary source or any error conditions, but for an analysis tool this is minor.

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 compensate. It explains `days` explicitly: 'the accumulated trend over `days` (1-90, default 7)', and clarifies `coin` as 'one coin' with primary-source mode selection. While it doesn't enumerate all enum values, it covers both parameters' meaning and constraints, adding value beyond the raw 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 starts with '[DRILL-DOWN] Long/short positioning for one coin from REAL data' which clearly identifies the verb (get/retrieve), resource (long/short positioning for a single coin), and distinguishes it from the sibling get_positioning tool by calling itself a drill-down complement to the 8-leg synthesis. It also specifies the data sources (Hyperliquid+GMX, CFTC COT, exchange ratios) and return artifacts.

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 says 'Complements get_positioning (the 8-leg synthesis) with the raw who-is-long-where view', giving a clear alternative and relationship. The '[DRILL-DOWN]' prefix signals when to use it, and the 'Analytical, not advice' disclaimer plus 'Mirrors REST /charts/long-short/{coin}' further clarify its scope and context.

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