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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is fully covered without description help. The description adds genuine non-annotation value: a recommended call-ordering ('use this first') and a hard scope boundary against household content, which is behavior an agent cannot derive from the annotations. It omits anything about what the response contains, but an output schema exists to carry that.

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?

A single sentence with the actionable instruction front-loaded and zero filler, which suits a zero-argument context tool. The clause list is long and reads as a run-on, slightly diluting the priority of 'use this first.'

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 an output schema present, no parameters, and complete annotations, the description only needs to establish scope and trigger conditions, which it does. The one remaining gap is that it never says whose context is returned or under what auth assumptions (current authenticated user), leaving a small ambiguity for a troubleshooting entry point.

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, so there is no parameter semantics to document and the baseline of 4 applies. The description correctly adds no parameter noise, though it also does not clarify that no arguments are needed (e.g., that context is derived from the authenticated caller).

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 description enumerates the domains the tool covers (sign-in, permissions, plan access, household availability, feature availability, calendar connection status), which effectively conveys that it returns account-level context, and it explicitly excludes household content. It never states a plain verb+resource like 'returns account context for the current user,' so the agent must infer the resource from the name and the enumerated topics.

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?

'Use this first when troubleshooting...' gives an explicit priority and trigger conditions, and '—not household content' explicitly carves out the exclusion, which routes the agent toward get_household. It stops short of naming the alternative sibling tools (get_household, get_my_support_reports) by name, so the routing is inferential rather than fully specified.

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