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

Annotations already cover read-only, idempotent, closed-world behavior, so the description's job is to add context — and it does, disclosing the required scope (settings:read) and warning that opt-in authorises spending API keys. It does not describe response shape (e.g., ordering or pagination), but the added auth and cost context is genuinely useful.

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?

Two sentences, front-loaded with the resource and returned fields, then the constraint and prerequisite. Every clause carries information: return fields, opt-in restriction, and required scope.

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 naming the three returned facts (opted in, active, A/B variant), plus the auth scope and the MCP opt-in restriction. For a zero-parameter read tool this is complete enough to call correctly.

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 no parameters, so there is nothing for the description to disambiguate; the baseline 4 applies. The description correctly implies a caller-scoped result with no filtering options, consistent with the empty schema.

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 ('List the experimental ... features your account has access to') and enumerates what each entry reports: opt-in state, active state, and A/B variant. It doesn't explicitly distinguish itself from the sibling list_feature_flags / list_feature_access tools, so an agent must infer the difference from wording alone.

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 a clear context (checking your own account's feature access) and a firm exclusion: opting in is not possible via MCP, only on the Labs page. It does not name which sibling to call when the agent wants org-wide flag definitions or to change access, leaving that comparison implicit.

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