create_journal_entry

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

With no annotations, the description carries the full burden, and it does add real behavioral context: the debit/credit balance invariant and irreversible immutability after posting. However, the key question the immutability claim raises — does create_journal_entry itself post the entry, or is posting a separate step via post_journal_entry? — is left unanswered, and nothing is said about permission requirements or what is returned.

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?

Three tight sentences, front-loaded with the action, then requirements, then the behavioral warning. Every sentence carries weight; only the brand mention 'in KikoBooks' is mildly expendable.

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 mutation tool with a nested object, no annotations, and no output schema, the description covers the balance requirement and post-creation immutability but omits whether the result is a draft or posted entry, what identifier is returned, and how imbalance errors surface. It is adequate but leaves the agent guessing on the create/post lifecycle.

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?

Only one top-level parameter, and the description reinforces the required fields (entry date, lines) and the balancing constraint. The nested schema already documents accountId, debitAmount/creditAmount exclusivity, and the debit-equals-credit rule, so the description adds modest but non-zero meaning. With a single param and adequate nested schema documentation, this is near the baseline-plus range.

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 ('Create a manual journal entry in KikoBooks'), and the immutability note implicitly separates this tool from the sibling post_journal_entry and reverse_journal_entry. It does not name those siblings directly, so an agent still has to infer the create-vs-post boundary rather than being told it.

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 only implied: 'manual' entry plus the note that corrections require reversal entries suggests when to reach for this tool versus post_journal_entry or reverse_journal_entry. It never states the condition that selects this tool over its siblings, nor whether the entry is created as a draft to be posted later.

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