get_unreconciled_splits

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

No annotations are provided, so the description carries the full burden. It discloses the CLI-like output structure (showing X-Y of Z indicator, one line per split, summary footer reflecting full set even when clipped) which is genuinely useful behavioral context. It clearly documents the pagination semantics and 'honest headline' behavior. While it doesn't mention read-only status explicitly, the get_ prefix and 'get' verb make it clear this is a read operation. Minor gap: no mention of performance or error conditions, but the behavioral details disclosed are strong.

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-structured with a leading summary sentence, prose paragraphs explaining output format and pagination, and a clearly formatted Args section. Every sentence adds information. Slightly verbose in the output-format explanation (showing indicator explanation could be compressed), but the structure is clean with no repetition of schema defaults that are already visible.

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?

Has an output schema and 5 parameters with 0% schema coverage. The description compensates thoroughly for the parameters and documents output format (compact lines, verbose JSON, count-only mode) and pagination semantics. It's complete for a read-only side-effect-free tool with a good output schema. Minor gap: doesn't clarify how 'unreconciled' relates to reconciliation status, but the tool is focused enough that the description is largely sufficient.

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 must compensate entirely, and it does excellently. Every parameter is documented with format details: account ref formats (full path, %short GUID, full 32-char GUID), as_of_date format (YYYY-MM-DD), limit default/max/special value (50, 250, 0=count only), offset semantics (0-indexed first row), and verbose behavior (full JSON with GUIDs, amounts, totals, showing indicator as structured field). This exceeds what the bare schema provides.

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?

Description clearly states verb (Get) + resource (unreconciled splits) + scope (for an account). The sibling tools like list_transactions, get_balance, and set_reconcile_state are distinct enough, and this description clearly distinguishes pagination/limit behavior making it easy to tell apart from get_reconciliation_status or reconcile_account.

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?

Provides explicit guidance on when to use (unreconciled splits for an account), how to page with offset, that limit=0 returns count only, and when to use verbose=true. It also clearly distinguishes the compact one-line format from full JSON, and explains the account ref formats (full path, %short GUID, or full GUID). This is explicit usage guidance with no ambiguities.

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