get_liquidation_candidates

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

Without annotations, the description carries the transparency burden. It conveys a read-only behavior through 'Find' and 'Returns', and adds a useful behavioral trait by specifying 'pre-indexed health data', implying a precomputed index rather than real-time queries. This goes beyond the schema and name, providing useful operational context.

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 with no filler. It front-loads the primary action and then summarizes the return criterion. Every word earns its place, making it appropriately sized and easy to parse.

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 no output schema and no annotations, the description should explain what is returned. It says 'Returns those below the health factor threshold' but doesn't specify whether 'those' are account addresses, objects, or how the optional parameters interact. The basic intent is covered, but return format and edge cases are missing, making it minimally complete.

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 the baseline is 3. The description mentions 'health factor threshold', which aligns with the 'threshold' parameter, but doesn't add further insight beyond the schema for 'chain', 'limit', or 'addresses'. No additional value to raise the score.

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 uses a specific verb ('Find') and resource ('accounts eligible for liquidation'), and distinguishes itself from sibling tools like get_health_factor (checks a specific user) and liquidate_txn (executes liquidation). It clearly states the condition (below health factor threshold) and the data source (pre-indexed health data), making its purpose unambiguous.

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 implies when to use it (when you want to find liquidation candidates) but does not explicitly mention alternatives or exclusions. Sibling tools like get_health_factor or liquidate_txn could be contrasted, but the description doesn't guide the agent on choosing between them. Usage context is present but underdeveloped.

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