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

The description explicitly says 'Reads only,' but the annotations declare readOnlyHint: false. This is an annotation contradiction: an agent cannot trust whether the tool mutates state or not. The aggregation behavior and per-currency warning are helpful, but the contradiction dominates this dimension.

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 sentences deliver the core question, the aggregation components, the currency constraint, and the key sibling distinction. There is no filler, and the most decision-relevant 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 no output schema, the description does a good job explaining the return shape: one row per currency, with received, applied, refunded, and still-held components. It also warns against summing across currencies. The only notable gap is the read-only contradiction, which affects trust rather than completeness.

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 schema already documents as_of and client. The description adds some interpretation, such as 'one client or everyone' for the client parameter and the no-cross-currency aggregation rule, but it does not add substantial parameter-level meaning beyond the schema.

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 answers a specific client question: 'how much of theirs am I holding?' and describes the resource as aggregated client-held funds across received, applied, refunded, and still-held amounts. It also distinguishes itself from deposit_list by emphasizing balance aggregation rather than individual deposits.

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 gives clear context: use this for one client or everyone and for aggregate balances, and explicitly names deposit_list as the alternative that shows each individual deposit. It does not fully enumerate all sibling alternatives, but the core read-vs-detail distinction is present.

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