register_payment

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

Annotations already declare destructiveHint=true, idempotentHint=false, and openWorldHint=true, so the safety profile is known. The description adds one useful hard constraint (at most 5 entries per invoice) but omits the most consequential behavior: that with additive=false ALL existing payments are replaced, which is the actual destructive path. It also says nothing about permissions, error conditions, or whether the invoice state changes.

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?

Two short sentences with the purpose front-loaded and no filler. The second sentence duplicates the schema's maxItems=5 constraint, so it is mildly redundant, but it is short enough not to harm readability.

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 mutation with no output schema, the description should warn about the additive=false replacement path and indicate what the call returns or changes. It covers the entry-count cap but leaves the agent without the information needed to avoid accidentally wiping existing payments.

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 100%, so every parameter (company, additive, payments, invoiceNumber, plus nested date/method/amount) is already documented in the schema, including the additive replacement semantics. The description's only parameter-adjacent content is the max-5 limit, which merely restates the schema's maxItems constraint. Baseline 3 applies.

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 uses a specific verb and resource ("Register payments on an invoice"), which is clearly distinct from siblings like create_invoice, reverse_invoice, or create_receipt. It stops short of naming a sibling or stating how it differs from related write operations, so it is clear but not fully differentiated.

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 by the purpose statement: an agent can infer this is the tool for recording payment against an existing invoice. There is no explicit when-to-use, no mention of prerequisites (does the invoice need to exist in a specific state?), and no guidance on choosing between this and receipt-related tools.

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