Merit Write Customers Confirm

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

Annotations already declare destructiveHint=true and idempotentHint=false; the description adds the confirmation gating contract (requires confirmation_code plus confirmed=true) and the two-step preview/confirm nature, which is genuinely useful beyond the annotations. It stops short of saying what data is destroyed or that repeats are non-idempotent.

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 key fact that this is the confirmed/executing half of a preview-confirm pair, and the sentences are short. The final 'Create or update customers' sentence is redundant with the action line that follows it.

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 destructive, non-idempotent write tool with nine mostly-optional parameters and no output schema, the description leaves critical gaps: what payload/filters must carry, how confirmation_code is obtained, and what side effects occur. It covers the workflow contract but not enough to call it correctly.

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% across 9 parameters, so the description must compensate. It only explains confirmation_code and confirmed; id, bank_id, filters, payload, delivnote, and add_attachment are entirely undocumented anywhere, leaving the agent to guess what payload must contain.

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 operation ('Executes a previously previewed write operation from merit_write_customers') and names the action customer_upsert, which distinguishes it from merit_write_customers (preview) and merit_write_sales_confirm. The purpose is clear, though the trailing 'Create or update customers' restates the action rather than adding scope.

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?

Gives the triggering condition explicitly ('when called with confirmation_code and confirmed=true') and ties this tool to a prior call to merit_write_customers. It communicates the preview-then-confirm workflow well but never states when NOT to use it (e.g., bypassing confirmation) or what happens if the code is stale.

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