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

Annotations already declare read-only, idempotent, non-destructive, but the description goes well beyond them: positive amounts only (credits/refunds excluded), posted transactions only, largest-first ordering, and a warnings array flagging banks that failed to contribute with reconnect_url. That is exactly the kind of data-quality caveat an agent cannot get from annotations.

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?

Four sentences, each carrying new information, front-loaded with what is counted and how it is grouped. No filler, no restatement of the title.

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?

No output schema exists, and the description compensates by describing the return shape (per-group count, average, total_groups, warnings) and the grouping key formats. An agent can predict the response without trial calls.

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 defaults for limit (20, max 100), start_date (30 days ago), and end_date are already documented in the schema. The description restates the limit and window defaults but adds no syntax or interpretation beyond them; baseline 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?

States a specific verb and resource with precise aggregation semantics: total posted spending grouped by category, merchant, month, or week. That is unmistakably distinct from list_transactions or search_transactions in behavior, but the description never names a sibling, so differentiation is inferred rather than explicit.

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 default 30-day window and the group_by options imply the intended use case, but there is no statement of when to pick this over get_monthly_cashflow or get_merchant_history, and no exclusions. An agent must reason from the described output shape to choose correctly.

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