ck_get_account_balances

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

Discloses rich behavior beyond the annotations: staleness thresholds (7 days linked, 35 days credit report), recency of credit-report data (2–5 weeks, no last 4), sign convention (liabilities negative, matching transactions), available-credit formula, and the default hiding of duplicate rows. Annotations only cover the safety profile; the description carries the substantive domain rules.

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?

A single dense paragraph that is front-loaded with what the tool returns before the qualification rules. Every sentence carries information, though the lack of any separation between return-shape and parameter/source guidance makes it slightly harder to scan.

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?

With no output schema and no annotations covering return semantics, the description fully documents the payload: field set, source provenance, freshness/staleness, sign convention, and duplicate handling. Nothing an agent needs to interpret the results 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 coverage is 100%, so baseline is 3, but the description adds meaning: refresh is framed as 'fetch live first' on top of local data, and include_matched is tied to the matched_to field and the duplicate-hiding default. This enriches both parameters beyond their schema text.

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+resource (get account balances) and immediately enumerates the returned fields (institution, type, last 4, current balance, available credit, credit limit, as-of time). It also anchors itself against siblings by noting the data comes from the local database filled by ck_sync_transactions, so an agent can distinguish it from summary/transaction tools.

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?

Gives clear operational context: pass refresh:true to fetch live first, and include_matched:true to surface credit-report duplicates. It explains the two source categories and their freshness, but never explicitly contrasts itself with siblings like ck_get_account_summary or ck_list_transactions, so there are no stated exclusions/alternatives.

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