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

Annotations declare readOnlyHint=true and destructiveHint=false; the description is consistent with that by saying it returns an unsigned transaction that the wallet signs. It adds real context beyond the annotations by explaining the settlement flow: stock sold, debt repaid, remainder returned in USDG.

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?

A single front-loaded sentence that identifies the artifact (unsigned transaction), the action, and the outcome. No repeated or filler content.

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?

For a three-parameter preparation tool with full schema coverage and no output schema, the description covers what is produced and what happens mechanically. It stops short of stating prerequisites (an existing long position) or that the result must be signed and submitted afterward.

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 three parameters are already documented, including percent's 1-100 range and default. The description's 'all or part' only echoes what the schema already says, so 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?

States a specific verb and resource: prepares an unsigned transaction that closes a leveraged long on a stock. Naming 'leveraged long' implicitly distinguishes it from close_short and close_pair, but no sibling is called out explicitly.

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 phrase 'closing all or part of the wallet's leveraged long' implies the precondition of an existing open long, but there is no explicit when-to-use guidance or routing to alternatives such as close_short or repay. Usage is inferable rather than stated.

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