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

Adds substantial behavior beyond the annotations: a metric with no data returns null, never zero, and the default/limited window (7–90, default 28) is disclosed. It also constrains downstream interpretation — state the dates, attribute figures to Google, do not claim causes — which is exactly the kind of context annotations cannot carry.

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-loads the returned metrics, then period semantics, then null/comparison caveats, then presentation rules — a sensible priority order for a reporting tool. It is dense rather than padded, though the closing reporting instructions read as agent directives rather than tool behavior and could be tightened.

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 carries the return burden and does it well by enumerating the metrics and the current-vs-previous-period shape, plus the null convention. What remains implicit is whether results are a single totals pair or a per-metric breakdown series, which an agent might still need to confirm.

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%, and the underspecified parameter is `days`, which the description fully defines (range 7–90, default 28) and frames semantically as the window compared against the prior same-length period. site_id and user_goal are left to their schema descriptions; user_goal in particular gets no mention in the description.

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?

Names the exact resource (Google-reported metrics for the location) and enumerates the metrics returned: views, calls, website clicks, direction requests, messages, bookings, food orders. The time window (last `days`, compared to the prior same-length period) is stated, which separates it from aggregate siblings like get_google_business_summary. It never names a sibling alternative, so differentiation is inferred rather than explicit.

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 concrete rule for when to go elsewhere: use assistant_context for exact period comparisons and reporting coverage. It also sets explicit when-not conditions for comparing (only when both totals are reported; missing previous data is not zero, not an increase, not 'no activity'). It stops short of routing the agent against neighbouring tools such as get_google_business_summary or get_growth_dashboard.

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