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

Beyond the annotations (destructiveHint: true), the description discloses chain-specific behaviors: EVM requires sign_approve first if need_approved=true, while Solana generates a fresh signable payload. It also labels the operation as '[write]', adding context about side effects. This exceeds what annotations alone provide.

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 two concise sentences, front-loaded with the core action ('[write] Sign the main swap tx for a staged session') and followed by essential chain-specific guidance. No wasted words; every sentence adds value.

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 multi-step signing tool, the description covers the key purpose and chain variations, and the schema handles parameter requirements. However, it does not mention what the tool returns (e.g., a signed transaction) or explicitly state that it must follow check-in/prepare steps, relying on sibling names and schema for that context. Still, it is reasonably complete for an agent familiar with the workflow.

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?

The input schema has 100% coverage with descriptions for all three parameters, so the description does not need to add parameter details. The description references need_approved=true which relates to a previous step, but the schema already fully documents the parameters. Baseline 3 is appropriate given full schema coverage.

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 clearly states the tool's function with a specific verb ('Sign') and resource ('main swap tx for a staged session'), distinguishing it from sibling dex_tx_swap_sign_approve by focusing on the main swap transaction. The chain-specific notes further clarify scope.

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 provides context on when to use this tool: it is for staged sessions and explicitly mentions the prerequisite of calling sign_approve first on EVM when need_approved=true. It does not explicitly state when not to use it, but the chain guidance and naming of the sibling sign_approve give clear comparative usage hints.

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