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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered structurally; the description adds genuine business context by explaining that the customer stops both receiving and paying for the items. It omits billing-side behavior such as proration, refunds, or whether a recalculation/invoice is triggered — material for a destructive billing mutation.

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?

Three compact clauses with the 'WRITE:' marker and the endpoint front-loaded. Every sentence carries distinct information: action, selector, consequence, transport.

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 two-parameter destructive billing write with no output schema, the definition covers the core action but not the outcome shape or edge behavior (partial failures, proration, effect on the next invoice). Adequate, not sufficient for a billing mutation.

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 50%: the item id format and the 'not internal_id' distinction live in the schema, not the description. The description only echoes 'by item id'. It does not mention the 1-50 item bounds or that subscription_id is the numeric id, leaving the compensating burden largely unmet.

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 verb and resource ('Remove items from a subscription') plus the selector ('by item id'), which clearly separates it from add_items and edit_items. The business consequence ('customer stops receiving and paying') reinforces intent. It stops short of naming the sibling it is most easily confused with (edit_items) explicitly.

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 implied by the verb and the stated consequence, but there is no explicit when-to-use/when-not guidance, no prerequisite (e.g. subscription must be active), and no routing to alternatives such as reducing quantity via edit_items instead of removing the item.

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