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

Annotations disclose this is a write (readOnlyHint=false) but non-destructive (destructiveHint=false). The description adds meaningful behavior beyond that: the fallback-to-judge semantics and that it returns the updated list_outflows answer, so the agent knows the effect is recording a verdict rather than mutating raw data.

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 tightly packed sentences: the action and its precondition first, then parameter-handling rules, then the return. No filler and the most important information is front-loaded.

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 an output schema present the return need not be explained, and the nested scope/dateRange parameters are fully schema-documented. The description covers the judge fallback and the data source, leaving only minor implicit details (permissions, reversibility) unstated.

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 100%, so the baseline is 3, but the description adds real meaning by explaining the verdict/transactionIds interaction and the default scope ('every unresolved row'). That conditional coupling of parameters is not obvious from the schema alone.

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 ('Decide where an "unresolved" debit went') and names its data source (list_outflows), which makes the operation concrete. It does not explicitly distinguish itself from the sibling adjudicate_transfers, so an agent must infer that this handles outflows while that one handles transfers.

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 clear conditional guidance: pass verdict/transactionIds when the user has stated the answer; omit verdict to let the AI judge decide the named rows or every unresolved row. The trigger (unresolved debits whose documentary claims conflict) is stated, though no explicit exclusion or alternative tool is named.

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