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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, and the description goes beyond them by stating the tool 'does not run commands, create resources or accept credentials' — a meaningful safety disclosure for a setup-planning tool. It also discloses the trust boundary between the default demo and the owner-authorized controller path. Minor ambiguity remains from the phrase 'Default creates an isolated Free read-only demo,' which reads oddly for a non-creating tool.

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 core purpose and eligibility in the first sentences, and every clause adds distinct information (scope, safety, routing). Slightly dense, and the 'default creates...' sentence could be tightened, but there is no filler.

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 compensates by enumerating the plan's contents (installer hash, recipe schema, prerequisites, authority boundaries, cleanup). It does not state the concrete response shape or format, which is the remaining gap for a zero-parameter discovery tool.

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?

The tool takes zero parameters, which is the baseline-4 case; there is nothing for the description to disambiguate. The description usefully clarifies that the default-vs-controller distinction is not parameter-driven but determined by the caller's environment.

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 ('read-only local setup plan for native OpenShell + Gate') and enumerates exactly what the plan contains (one command, installer hash, recipe schema, prerequisites, authority boundaries, cleanup). It also explicitly separates itself from the sibling family by naming gate_create_project as the entry point for non-OpenShell agents.

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 an explicit eligibility gate ('Only for OpenShell users; any other agent starts with gate_create_project') and names the exact alternative tool. It further splits usage into the default Free read-only demo versus a trusted local controller configuring an owner-authorized API, so an agent knows which mode applies and when not to call it.

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