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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the danger profile is known. The description adds real value beyond that: permission gating, the FREE-business exclusion, and the requirement to show a grace-period warning and resubscribe link before proceeding. However, it does not clarify what exactly is destroyed or how period-end cancellation behaves, which matters for a destructive write.

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?

The action and resource come first, followed by prerequisite gating and warnings; no sentence is filler. The wording is slightly dense and reads like a policy checklist, but nothing is redundant.

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 mutation with no output schema and 5 parameters, the description covers the critical operational facts an agent needs: the required confirmation literal, the access check, the FREE-tier exclusion, and the pre-warning obligations. Only the cancellationReasons parameter and the exact effect of period-end cancellation remain undocumented.

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 80%, so the baseline is 3, and the description exceeds it by supplying the exact confirm literal (UPDATE_SUBSCRIPTION) that the schema omits—the schema description only says 'for example DELETE.' This is important since confirm is not even in the required list. It says nothing about cancellationReasons or the true/false semantics of cancelSubscription, leaving a 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 verb and resource: 'Update subscription cancellation state for a custom-domain order in a managed community.' The note that 'business and community refer to the same thing and are interchangeable' helps scope it, though it also raises the question of how this differs from the identically-named 'business' and unqualified siblings, which is left unanswered.

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 explicit when-not conditions (FREE businesses cannot use it, never proceed when access is blocked) and a mandatory prerequisite workflow: call check_business_tool_access before collecting inputs, and surface the grace-period warning and resubscribe link first. It stops short of naming alternative tools such as the business/community variants or plan-cancellation siblings, so the 5 bar for alternatives is not met.

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