Merit Write Financial

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

Beyond annotations (readOnlyHint=true, destructiveHint=false), the description adds significant behavioral context: it is preview-only, returns a confirmation_code, uses different API versions based on currency (v1/v2), and raises errors if IBAN or PaymentDate are unresolved. These details are valuable and extend beyond what annotations provide.

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 long and includes bullet points with action-specific details. It front-loads the key preview-only behavior, but the exhaustive listing of actions and parameter details makes it less concise. It is adequately structured but could be more streamlined.

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?

Given the complexity (multiple actions, 9 parameters, no output schema), the description is incomplete. It fails to explain general schema parameters like id, filters, payload, add_attachment, delivnote, bank_id, confirmation_code, and confirmed. It also provides minimal detail for most actions, leaving the agent uncertain about how to use the tool for actions other than purchase_invoice_payment_create.

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. It provides detailed parameter semantics for the purchase_invoice_payment_create action (field types, defaults, auto-fetch), but other actions (tax_upsert, dimensions_add, items_add, item_update) receive only one-line summaries with no parameter details. The schema has 9 parameters with no descriptions, and the description covers only a subset, leaving significant gaps.

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 clearly states the tool is a preview-only write tool that does not execute changes, returning a confirmation_code for confirmation. It lists specific actions (purchase_invoice_payment_create, tax_upsert, etc.) and distinguishes itself from the sibling confirmation tool (merit_write_financial_confirm). The purpose is specific and well-defined.

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 implies that this tool should be used for previewing financial write operations before confirming with merit_write_financial_confirm, but it does not explicitly state when to use this tool versus other write tools like merit_write_customers or merit_write_purchases. Usage guidelines are implied but not explicit.

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