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

With no annotations, the description carries the whole burden and does real work: it declares read-only behavior, result ordering, that non-member shops are refused, and that amount fields are gated behind a see_prices permission (implying redaction). It leaves pagination behavior and the default page size unstated, and cursor-based paging is a meaningful omission for a list endpoint.

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?

Four short sentences, front-loaded with the resource and ordering, and no filler. The telegraphic fragments ('Read only.', 'Amounts need see_prices.') are efficient but slightly strain parseability.

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?

An output schema exists, so return values need not be described, and authorization/permission behavior is covered well. However, for a cursor-paginated list tool the description never explains how to iterate pages or what the cursor represents, which is the main gap an agent must close from schema alone.

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 only 33%: limit is documented in the schema but cursor and shop_id are not. The description explains shop scoping ('in one shop') and the meaning of the returned id, but says nothing about cursor or how to page, so it does not compensate for the coverage gap.

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 resource (card and bank payments), scope (one shop), and ordering (newest first), so it is clearly a list operation rather than payments_get or payments_connectLink. The added note that each id is the charge_id consumed by invoices.refund ties the output to downstream use, but it never explicitly contrasts itself with the sibling payment readers.

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?

Provides a downstream-use hint (take an id and pass it to invoices.refund) and states the read-only nature, but gives no explicit 'prefer payments_get when you already know the id' or any when-not-to-use guidance against the many other list tools.

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