Get transactions

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

Annotations already cover read-only, idempotent and non-destructive, and the description still adds substantial behavior: it transparently discloses internal continuation-page traversal, that only the newest matching rows are returned, the context-protection cap (default 50, max 200), the sign convention (debits negative, direction DBIT), the absence of any payment action, and a privacy constraint ('show the result only to the account owner'). These are non-obvious traits an agent could not infer from structured fields.

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?

Front-loaded with the core purpose, then progressive detail on paging, filtering, alternatives and constraints. Every sentence carries actionable information; nothing is filler, and the only repetition (50/200 cap) is restated to justify the context-safety rationale.

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 six-parameter, open-world read tool with an output schema, the description covers everything an agent needs: paging behavior, truncation limits, filtering strategy, alternatives, sign conventions and a privacy caution. Return-value structure is correctly left to the output 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 coverage is 100%, so the baseline is 3, but the description adds rationale the schema lacks: why the limit exists (so a long history does not fill context) and that narrowing dates or searching is preferable to raising it. It does not add syntax or format detail beyond the schema, so it stops short of 5.

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 plus scope: 'Read-only transactions for a date range.' It also clarifies the retrieval model (follows Enable Banking continuation pages, then returns newest matching rows) and names the sibling tools to use for a different job, so an agent can separate it from recurring_charges without opening any schema.

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?

Explicit routing guidance: 'Filter with search, or narrow date_from and date_to' and 'For a summary, use recurring_charges or the monthly spending resource instead of raising the limit.' It gives both the positive usage pattern and the when-not/alternative, which is exactly the decision an agent faces.

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