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

Annotations already declare readOnly=false, destructive=false, idempotent=false, openWorld=true, but the description adds genuinely new behavioral context: it returns an unsigned transaction plus a review link and never signs. This clarifies the prepare/execute boundary that the annotations don't express.

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?

Two tight sentences with the action and precondition front-loaded, and the key behavioral guarantee (never signs) placed last for emphasis. No wasted words.

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 3-param mutation-prep tool with annotations but no output schema, the description covers the effect and return shape adequately. It falls short on param meaning (undocumented wallet/loanId) and does not address auth or the relationship of 'wallet' to the caller.

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%: engine is described, but loanId and wallet carry no descriptions or enums. The description adds nothing about any parameter's meaning, format, or role, so it fails to compensate for the coverage gap.

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 (Prepare cancelling) and resource (a loan) with a precise precondition: 'still waiting for funding', plus the side effect of taking collateral back. It distinguishes itself from execution-type siblings via 'returns the next unsigned transaction', though it doesn't explicitly name an alternative tool.

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 'still waiting for funding' clause implies when this applies, giving an implicit precondition. However, it names no alternative tool (e.g. the borrow-collect/sign counterpart) and states no exclusions, so routing is left partly to inference.

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