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

The description discloses the key side effect not present in annotations: it posts exactly one journal entry against Opening Balance Equity, dated the day the books open. It also clarifies sign semantics (positive for an asset, negative for money owed). It stops short of explaining reversibility or idempotency, but it gives the critical behavioral context for a mutating call.

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 short sentences front-load the purpose and operational rule, with no filler or repetition. Every sentence adds value: what it does, what it posts, why it matters, and how to pass the amount.

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?

The description is solid for a small mutating tool and an output schema exists, so return format need not be described. The biggest completeness gap is the relationship between companyId, accountId, and cardId: the schema only marks companyId required, and the description never says the caller must also provide one of the account/card identifiers or what happens if both are supplied.

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?

The description meaningfully clarifies the amount parameter (establish amount, not the difference, with sign conventions) and ties asOfDate to the day the books open. However, the schema's description coverage is low-quality ('UUID value wrapper'), and the description does not explicitly state that one of accountId or cardId is required alongside companyId, nor what companyId represents. It compensates only partially.

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?

The description uses a specific verb and resource: it records the opening balance of a bank account or card and posts one journal entry against Opening Balance Equity. This is materially more precise than the title and distinguishes the tool from generic journal-entry or transaction-categorization siblings.

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 description makes the intended context clear: use this when a bank account or card held money before the transaction feed's history begins, and it explicitly warns to pass the amount to establish rather than the difference. It does not name alternative tools or state when not to use them, but the context is strong enough to guide selection.

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