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

Goes well past the annotations by disclosing a human-gated elicitation requirement, that non-elicitation clients are refused while dry_run still works, that the human reviews a per-tier before->after diff, and that the multi-tier write is atomic. It also documents the -1 unlimited convention and the exact blast radius (limits object only).

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-loads the WRITE/human-gated warning before the mechanics, and nearly every sentence carries a distinct fact (guardrail, atomicity, -1, blast radius, alternative, sync step). It is dense but runs long; the alternatives and post-sync instructions could be tightened without losing meaning.

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?

Appropriately complete for a destructive, nested-object write with no output schema: safety gate, scope, sentinel value, and follow-up step are all covered. The one omission is what merge versus replace actually does to existing limit keys, which matters given destructiveHint=true.

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?

With 0% schema description coverage and a nested `updates` object, the description carries the burden and mostly delivers: tier-keyed structure, key->number shape via the example, -1 semantics, and dry_run behavior. The `mode` enum (merge vs replace) is never explained anywhere, which is a real gap for a destructive write.

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 (change usage limits on an app's existing tiers) and immediately anchors it with a concrete example (set ai_generations_daily to 200 on pro). It also draws a hard boundary against adjacent operations — 'this writes ONLY the limits object: it never touches Stripe, prices, or plan names' — so it is unmistakable versus update_plan_pricing or create_app_kit.

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?

Explicitly routes alternatives: changing prices or adding a tier is 'a different job: use create_app_kit or the dashboard.' It also names a preview path (dry_run), and gives a required post-condition (run `bun run plans:sync` and commit plans.json).

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