list_transactions

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

The description goes well beyond the readOnlyHint annotation, disclosing several non-obvious behaviors: the 'Showing X-Y of Z transactions' header prevents misinterpreting truncated results, limit=0 returns count only, the account filter switches to register form and shifts column semantics, and >4 splits collapse with a pointer to get_transaction. These details equip the agent with expectations that annotations alone cannot convey.

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 well-organized: a one-line summary, key behaviors, output format details, then parameter semantics. It uses formatting (backticks, bullets, indent) to keep dense information scannable. Every sentence adds functional value, and the most critical caveat (truncation indicator) 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?

For a tool with six parameters, no required fields, and multiple output modes, the description covers all operational aspects: filtering, pagination, count-only, format switching, register behavior, and split collapsing. The existence of an output schema means verbose JSON fields need not be enumerated. Nothing needed for correct invocation is missing.

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 0%, so the description carries the full burden—and it delivers. Every parameter is explained with functional meaning beyond type: account triggers register format, start/end dates use ISO, limit has a 0=count-only special case and max, offset is 0-indexed, and verbose toggles output structure. This is comprehensive and directly compensates for the schema's lack of descriptions.

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 transactions with optional filters.' It then details distinct output modes (compact text vs JSON), pagination, and filtering behaviors, making the tool's purpose concrete and distinguishable from siblings like get_transaction. It explicitly points to get_transaction for a full breakdown, reinforcing its own scope.

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 clearly states use cases: filtering by account, date, pagination, count-only, and choosing verbose JSON when machine-readable fields are needed. It names get_transaction as the alternative for full split details, providing a when-to-use derivative. It does not, however, contrast with search_transactions or explicitly say when not to use this tool, so it falls just short of full 5.

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