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

Annotations only declare readOnly/non-destructive/openWorld; the description adds genuinely non-obvious behaviour — data is scoped to the calling user's API key with no way to query another wallet, results are position-level rollups rather than fills, and an empty response means 'never closed a position' rather than 'holds nothing'. These are semantic traits the annotations could never convey.

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?

Front-loaded with the core distinction and the highest-risk warning, so skimming yields the right behaviour. It does repeat the 'closed only' point twice (the IMPORTANT sentence and the empty-result sentence), costing some length for a four-parameter read 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?

An output schema exists, so return shape needn't be described; the remaining gaps an agent could hit — user scoping, empty-result interpretation, and the position-vs-trade granularity — are all covered.

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 coverage is 75% (page, limit, and token_address are documented in the schema), so the baseline applies. The description adds nothing about the `token_address` filter, which is the one parameter whose usefulness ('how did I do on X') is implied but never spelled out, and says nothing about paging behaviour.

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?

Opens with a specific verb+resource and scope: closed positions the user has fully exited, with realised PnL. It explicitly separates itself from `get_my_balances` (open positions) and `get_my_closed_trades` (individual fills), so an agent can pick the right tool without opening any schema.

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?

Gives an explicit decision rule: positions for 'how did I do on X', trades for 'show me every trade'. It also states a when-not ('never tell a user they hold nothing based on an empty result') and names the alternative that answers holdings questions, which is precisely the failure mode for this tool.

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