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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is largely covered; the description reinforces it ('Read-only: it changes nothing') and adds genuinely new behavior: show steps and ask before running any command, and that commands prompt for secret values themselves. Good extra context beyond annotations.

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-loaded with the purpose and the ordered step list, then usage and safety constraints. Dense but every clause carries information; only minor compression is possible.

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?

With no output schema, the description effectively outlines the returned plan (export, keep data/sign-ins, deploy, env vars, auth redirects, domain, DNS switch, verify, disconnect), plus the DNS re-check flow. Nothing an agent needs to call it correctly is missing.

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% (baseline 3), but the description adds real meaning: pass dependency names from package.json, variable NAMES from .env.example, and 'never pass values or secrets'—clarifying the intent and safety boundary of env_names and dependencies beyond the 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+resource ('ordered, repeat-safe plan for moving an app built in an AI app builder...to the user's own host') and enumerates the concrete steps included. An agent can distinguish it from plan_dns_setup and plan_launch_steps without opening the 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?

Gives clear invocation context ('Call again after the DNS change to confirm, or use plan_dns_setup') and conditions for passing optional data ('If you can read the project, pass dependency names...'). Names an alternative tool but doesn't state explicit when-not-to-use exclusions.

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