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

Annotations already flag destructiveHint=true and openWorldHint=true, but the description adds substantial context beyond them: human approval gating, the deliberate decision to leave Stripe products/prices untouched so existing subscriptions are never affected, the two refusal conditions and how they are matched, and the required follow-up `bun run plans:sync`. Nothing here conflicts with idempotentHint or the other hints.

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?

Front-loading is excellent: purpose first, then the WRITE/human-gate warning, then context, then refusals, then the post-step. It is one dense paragraph whose sentences each carry information, though the middle context sentence is long enough to slow scanning.

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, human-gated write with no output schema and three parameters, this covers the safety profile, side effects, refusal behavior, subscription impact, and the follow-up sync step. The only minor omission is what dry_run returns, which is inferable from 'previews anywhere.'

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 0%, so the description has to carry the load. It meaningfully explains `dry_run` ('previews anywhere'), clarifies that `tier` is a slug matched against Stripe price ids, and ties refusal logic to it. `app_id` is only implied by 'an app's plan catalog' and its format is never stated, which keeps this short of a 5.

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 first sentence gives a specific verb and resource ('Remove a tier from an app's plan catalog') and immediately positions the tool against siblings: 'Every other plan tool edits tiers that already exist, so a catalog could grow but never shrink.' An agent can distinguish this from update_plan_meta/update_plan_pricing without reading any schema.

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?

It states exactly when a real write is possible ('needs an elicitation-capable client and the human must approve') versus when it is not ('dry_run previews anywhere'), and names the gap it fills that the other plan tools leave open. Refusal conditions (non-cancelled subscribers, last remaining tier) tell the agent when not to expect success.

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