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

Annotations only mark readOnlyHint=false/destructiveHint=false, so the description usefully clarifies that this is a simulated action with no money movement, that pricing comes from a real Jupiter quote, that it records realized P&L, and that it requires 'Authorization: Bearer <JWT>'. It doesn't say what happens if no open position exists or whether the operation is idempotent.

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?

Three dense sentences, front-loaded with the PAPER qualifier and the side-effect scope before the parameter hints. Efficient, though 'Pass one or `sells: [...]`' is slightly telegraphic.

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?

With six parameters, no required fields, low schema coverage, and no output schema, the description carries a lot of burden. It covers auth, simulation semantics, and P&L recording, but says nothing about return values or failure modes, so an agent still has open questions before invoking.

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 only 33%, and the description compensates for the core trading parameters by explaining the one-of selection among 'all', `fraction`, `amount_tokens`, and the `sells` batch form. However, `mint`, `ledger`, and the overall required-field story remain undocumented in both places, leaving real gaps.

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?

States a specific verb and resource ('sells an open paper position ... to USDC'), and the leading 'PAPER.' plus 'no money moves' immediately disambiguates it from real-execution siblings like signet_submit. An agent can tell what it does and which order-flow tool it is not without opening the 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 invocation-shape guidance ('Pass one or `sells: [...]`', fraction vs amount_tokens) but never states when to choose this over signet_submit/signet_action or what prerequisite state (an open paper position) must exist. Usage is implied by the word 'paper' rather than explained.

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