Merit Write Customers Confirm

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

Annotations declare destructiveHint=true, and the description confirms it's a mutating tool. The description adds details about actions (create/update customers/vendors) and notes that for vendor_update only Id is required. However, it does not describe behavior on failure, rollback, or what happens if confirmed=false, so some behavioral context is missing.

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 multi-sentence but each sentence adds information: purpose, actions, typical use, payload fields. It is front-loaded with the key fact that it is a confirmed mutating tool. Slight redundancy in describing 'Create or update customers and vendors' followed by specific actions, but overall efficient.

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 no output schema, the description does not cover return values. It lacks details on error handling, the effect of setting confirmed=false, or prerequisites beyond the preview step. For a confirm tool, this could be more complete, but the typical use case helps.

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?

With 0% schema description coverage, the description must compensate. It explains payload fields (Id, Name, etc.) and notes required parameters (action, confirmation_code, confirmed). However, it does not describe other parameters like id, filters, add_attachment, delivnote, bank_id, leaving some parameters undocumented. Partial coverage but adds value.

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 that the tool executes a previously previewed write operation from merit_write_customers, requiring confirmation_code and confirmed=true. It lists specific actions (customer_upsert, vendor_upsert, vendor_update) and provides a typical use case. This fully distinguishes it from sibling tools like merit_write_customers (preview).

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 specifies when to use the tool: after previewing from merit_write_customers, with confirmation_code and confirmed=true. It includes a typical use scenario involving vendor BankAccount synchronization. Though it doesn't explicitly state exclusions or alternatives, the context of a confirm tool is clear.

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