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

Annotations already establish read-only, idempotent, non-destructive, open-world behavior, so the safety profile is covered. The description adds genuinely new behavioral context: refresh=true forces a re-read from Google (a cost/freshness trade-off the agent would otherwise not know), the recommended count may be legitimately short of what was requested, and the same items surface in the owner-visible 'Next steps' surface. It stops short of describing pagination, size, or failure modes when Google is not connected.

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 snapshot scope, then the operational constraints, then the refresh flag — a sensible ordering with no filler sentences. The opening enumeration is long and dash-heavy, which makes it dense, but every listed item earns its place by telling the agent what it can answer without another call.

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?

There is no output schema, so the description carries the return-value burden, and it does so by enumerating the snapshot's sections and stating that recommendations come with evidence plus an action. With only three parameters and one required, the remaining gap is behavioral edge cases (unconnected listing, empty data) rather than missing invocation detail.

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 67%: site_id and user_goal are documented in the schema, but refresh has no schema description. The description compensates by explaining refresh='re-reads Google first', which is exactly the missing semantic (fresh fetch versus cached snapshot). user_goal gets no further treatment in the description, but the schema covers it adequately.

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 states a concrete resource: a single consolidated snapshot of a site's Google listing, and enumerates its contents (connection/verification, review and reply counts, mismatches, posts, performance, pending changes, freshness) plus prioritized recommendations with evidence and next action. That is far more specific than the title alone. It does not, however, differentiate itself from near-neighbours such as get_google_business_status, get_google_profile, get_google_performance, or get_google_portfolio_summary, so an agent still has to guess which of the Google read tools to call first.

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?

Usage is implied by the 'Next steps' framing — this reads as the orientation/summary call before acting on Google items — and there is explicit downstream guidance ('Follow assistant_context and the returned recommendations', 'give fewer rather than inventing steps', 'Do not offer unavailable booking links or video Google posts'). What is missing is any explicit when-to-use versus the sibling Google read tools (status, verification, performance, portfolio summary) and any statement of prerequisites such as the listing needing to be connected.

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