Balances

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, so the description's safety burden is low. The description adds useful scope behavior (default account vs whole client) and enumerates returned data, but it does not describe aggregation details, error conditions, or response shape. This is acceptable but not rich behavioral 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 a single compact sentence that front-loads the main returned fields and then states the scoping option. Every part earns its place, with no redundancy or filler.

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 two-parameter read-only tool, the description covers the returned categories and the account-scoping behavior, and it links to get_account_summary for account-key context. No output schema exists, but the field enumeration gives a workable picture of the response despite the absence of detailed return-structure documentation.

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%; both accountKey and wholeClient are already documented in the schema. The description's mention of 'default account' and 'whole client' largely paraphrases the schema without adding new semantic meaning. The baseline of 3 applies.

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 identifies the resource (balances) and enumerates the specific data returned: cash balance, account value, margin, unrealised P&L, and position/order counts. It also distinguishes between a single account and the whole client, making the tool's purpose recognizable even without an explicit comparison to sibling tools.

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 explains the main usage decision: one account by default or the whole client via wholeClient, and points to get_account_summary for account keys. It does not explicitly say when to avoid this tool in favor of siblings like get_positions or get_orders, but the clear scoping guidance covers most practical use.

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