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

Annotations already declare readOnlyHint=true, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description adds a useful behavioral caveat: 'Transaction IDs and types are endpoint- and company-specific.' This is value beyond annotations and warns agents not to assume ID portability. It doesn't address pagination or result limits, but the note about ID variability is meaningful 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 concise: a single sentence plus a short caveat. It front-loads the main purpose and keeps the additional note brief. It earns its place by adding the endpoint/company-specific caveat. It could be slightly improved by an explicit sentence on when to use it, but for a list operation this is acceptably compact.

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?

Given a read-only list tool with full schema parameter documentation and annotations covering safety, the description is nearly sufficient. The main gap is no explicit mention of pagination or result ordering, and no comparison with the many sibling list transaction tools. For a simple list tool with this annotation richness, the definition is largely complete. I'll give 4 because the missing routing guidance relative to siblings like brc_list_customer_op_bal_trans is a real but minor gap.

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 schema documents all three parameters. The description adds almost nothing about how the parameters affect the call, aside from the general caveat that transaction IDs and types are endpoint- and company-specific. The connectionRef parameter has a detailed inline description covering reuse and session-id rotation, which is helpful and embedded in the schema. Baseline 3 might apply since schema coverage is high, but the tool description itself provides no parameter semantics beyond the schema, and the caveat about transaction IDs is not tied to any specific parameter. Given that the schema carries the burden and the description contributes little, 2 is appropriate.

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 states a clear verb and resource: 'Returns customer account transactions.' This distinguishes it from the many brc_list_* siblings by its focus on 'customer account transactions.' However, it doesn't explicitly contrast with closely related sibling tools like brc_list_customer_op_bal_trans or brc_list_allocated_transactions, so it is clear but not fully differentiated.

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 usage: call this to list customer account transactions. It provides no explicit when-to-use guidance or alternative tool comparisons. The sibling list contains multiple transaction-related list tools, so an agent could benefit from explicit routing cues. The connectionRef parameter documentation gives some usage context about reusing the connection, but that applies to this tool's calling convention, not when to choose this tool over alternatives.

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