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

Annotations already declare readOnly=false, destructive=true, and idempotent=true; the description adds meaningful context by disclosing the blast radius ('Changes every future order of that subscription'), which is exactly what matters for a destructive write. It does not mention reversibility or auth requirements, keeping it short of a 5.

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 tight clauses led by 'WRITE:', then the concretized example, effect scope, and endpoint. Zero filler and front-loaded with the important signal.

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 4-param, all-required write tool with annotations covering safety and no output schema, the description gives purpose, scope, and endpoint adequately. Minor gap: no note on whether/how the change can be reverted.

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 100%, so the schema documents each parameter. The description adds value by showing the combined semantics ('every 2 WEEK' pairs interval_count with interval), reinforcing how the two fields interact beyond the per-field schema text.

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 (change) plus resource (subscription frequency/billing and delivery), with concrete examples like 'every 2 WEEK or every 1 MONTH'. This clearly distinguishes it from siblings such as set_next_billing_date or pause_subscription.

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 explains the effect scope ('Changes every future order of that subscription'), which implies when to use it, but it names no alternative or exclusion (e.g. vs. changing just the next date). Usage is inferred rather than explicitly guided.

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