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

Beyond the annotations (readOnly false, destructive false, openWorld true), it discloses the full lifecycle (stays Unfinished and editable, not in official accounts until Approve), the confirmation-by-default behavior, the external-reach warning, and the Cotlet API key scope requirement. This is rich, non-redundant behavioral context for a mutation tool.

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 core action and mostly earns its sentences, but there is mild redundancy between 'Creates the receipt the way New journal receipt does' and the opening sentence, and the two confirmation statements ('By default you confirm each call' and 'confirm with the user before each call') partially overlap.

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, the description still covers everything needed to invoke correctly: required inputs, row signing and balancing rules, resulting state, approval dependency, confirmation policy, and auth prerequisites. Nothing material is missing for this mutation tool.

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 required fields are already documented, but the description adds genuine semantics: plus equals debit, minus equals credit, and rows must balance. That balancing constraint is meaning the schema does not convey.

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 precise verb and resource ('Save a journal receipt with debit and credit rows as Unfinished') and clarifies it mirrors Procountor's 'New journal receipt' flow. An agent can distinguish it from procountor_list_journal_receipts and the invoice/purchase tools immediately.

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?

Explains the operative state conditions: the receipt stays Unfinished and only enters official accounts after someone approves it, and requires confirmation with the user before each call. It gives clear context for when to use it, though it does not name a sibling alternative (e.g. the approve tool) explicitly.

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