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

Annotations only declare read-only/idempotent; the description adds substantial context beyond that: sorted descending by impressions, null im pressions with an upper-bound threshold for low-volume keywords, a maximum 12-month window, Google's 18-month retention limit, and empty arrays for months with no data. These are exactly the quirks that would otherwise trip up a caller.

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?

Four sentences, front-loaded with what it returns, then the return shape, then ordering and the null/threshold caveat, then range limits. Every sentence carries information an agent needs; nothing is padded.

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, and the description compensates fully by spelling out the response shape { months: [{ month, keywords: [...] }] } along with sorting, null semantics, and empty-month handling. Combined with a fully described input schema, an agent has everything needed to call and interpret it.

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 100% and defaults for from_month/to_month are already documented there, so the baseline is 3. The description adds real value by tying the from_month/to_month pair to the 12-month cap and the 18-month retention window, giving the agent a bound the schema doesn't express.

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: the search queries that surfaced a Google Business Profile location in Search and Maps, aggregated month by month. The metric set (keyword, impressions, threshold) makes it unmistakable versus sibling tools like profiles_stats or google_business_location_get.

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 data description and the 12-month range / 18-month retention constraints, so an agent can infer the tool fetches historical monthly keyword data. However, it never states when to prefer this over profiles_stats or other performance tools, nor does it name an alternative for different metrics.

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