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

The description adds real behavioral content the annotations do not: each row carries debit, credit and bank_ref, the response includes totals of the rows returned, and filtered totals do not balance. But it frames the tool as a pure read ("List") while annotations declare readOnlyHint=false, leaving the agent unsure whether the call has side effects — a discrepancy that matters more than the extra detail helps.

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?

One dense sentence front-loads the action and the filters, and two short clauses add the totals caveat and cost. Nothing is redundant, though "Free." and "source server" are terse enough to need a second read.

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 usefully discloses the row shape (debit, credit, bank_ref) and that totals are returned, which is exactly what an agent needs to plan the call. Gaps remain around pagination/limit behavior and the currency requirement, though both are covered in the schema.

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 all nine parameters are already documented in the schema, and the description only restates the filter set (account, source, source_id, date) without adding format or interaction detail. Baseline 3 applies where the schema carries the semantics.

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 opens with a specific verb and resource ("List the ledger lines for a period") and enumerates the supported filters (account, source server, source_id, date), so an agent can tell this returns individual ledger entries rather than an aggregate. It stops short of naming siblings such as trial_balance or ledger_report, so the boundary with those tools must be inferred.

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?

"Filtered totals do not balance" is a useful warning that steers an agent away from treating filtered output as a reconciliation figure, which implicitly points to trial_balance for balanced totals. However, there is no explicit when-to-use/when-not-to-use guidance or named alternative, so routing is only implied.

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