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

Annotations already declare non-read-only, idempotent, non-destructive, closed-world behavior. The description adds genuinely useful context the annotations do not: auth requirement, the 10-position cap, and tiering ('forced-close levels (paid)', 'Needs a signed-in connection (free)'). However, it frames the tool purely as a read ('each read with the facts now') and never mentions that `action` can set or clear a position, leaving the primary mutation behavior undisclosed.

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 scope ('Up to 10 of your own positions') is front-loaded and the telegraphic fact list is information-dense rather than padded. The two trailing sentences carry distinct load (disclaimer, prerequisite). Slightly telegraphic style costs readability but no sentence is wasted.

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?

An output schema exists, so return values need no explanation, and the auth/tier/prerequisite info is present. The gap is the write path: for a tool with `set` and `clear` actions and readOnlyHint=false, an agent reading only the description would not know it can create or remove a tracked position, which is required to invoke it 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?

Schema description coverage is 100%, so all 9 parameters (coin, side, entry, action, cursor, detail, leverage, size_usd, liquidation) already carry meaning in the schema. The description only implies the position-tracking shape and hints at liquidation via 'forced-close levels (paid)'; it adds no syntax or format detail beyond that. Baseline 3 applies.

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 names a concrete resource and scope: 'Up to 10 of your own positions on your account,' and enumerates what is attached to each (price vs entry, whale lean, tracked accounts, liquidation levels, fee). An agent can tell this apart from siblings like whale_radar or coin_brief. It stops short of a 5 because the core verb is only 'read' — the ability to record and clear positions via the `action` parameter is never surfaced.

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?

'Needs a signed-in connection (free)' gives a real prerequisite, and 'No view on the position' signals this is data, not advice, which helps distinguish it from signals-style siblings. But there is no explicit when-to-use vs. when-not guidance and no named alternative for the account/holdings read case within this 23-tool sibling set.

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