get_transactions

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

Annotations already cover the read-only/idempotent profile, yet the description adds genuinely non-obvious behavior: fetched broker rows are written to a local append-only ledger, 'no broker writes'. It also discloses pagination via next_cursor, that the page header carries window-wide totals/counts, and that 'raw' returns one source at a time.

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 what and ordering, then parameter semantics packed densely with zero filler. The detail_level sentence is a run-on that mixes three modes plus the one-source-at-a-time constraint, but no sentence is wasted.

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?

An output schema exists, so return values needn't be explained, yet the description still usefully sketches the page header's totals and cursor. With 7 parameters and 0% schema coverage, the only real omission is the unexplained 'symbol' filter.

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 0%, so the description must carry the load, and it does: ISO date format with a 90-day default, account values ('all', 'toss', 'kis' or a label), limit bounds 1-500 with default 100, cursor as next_cursor, and full semantics for the three detail_level modes. Only the 'symbol' parameter is never mentioned, leaving one of seven undocumented.

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 resource and scope: 'Your trades across every Toss and KIS account, newest first, one page at a time.' This clearly separates it from holdings/snapshot siblings by making it a historical transaction feed. It does not explicitly name a sibling it is not, which keeps it just shy of a 5.

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?

Usage is implied rather than stated: the agent can infer this is the trade-history listing versus get_holdings or get_trading_pnl, but the description never says when to prefer this tool or when to use an alternative. No exclusions or prerequisites are given.

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