googlepatents_coverage

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

No annotations are present, so the description carries the full burden. It clearly frames the tool as read-only and aggregate (Returns how many...), and the sentence 'Public data, sourced from Google Patents' own search API' discloses the data provenance and does not suggest authentication or mutation. It could mention output format or response size, but for a zero-parameter coverage tool the main behavioral surface is well covered.

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?

The description is organized with a short title-like first sentence followed by an expanded returns sentence and a provenance note. It is not overly long and is still readable, but the first and second sentences essentially state the same grant-per-country-per-year idea twice, making the structure slightly redundant rather than maximally concise.

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?

For a tool with no parameters and no output schema, the description provides enough context to call it correctly: it states the data source, the granularity (per patent office/country and per year), and that it covers all authorities. The agent knows what will happen when invoked and roughly what to expect in the response. More detail about the exact response shape or whether the result is a single object or paged would make it even more complete.

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 has zero declared parameters and the input schema is empty, matching the low parameter count exactly. There are no parameter names, defaults, enums, or formats to document, so the baseline score of 4 applies and the description justly adds no parameter-level detail.

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 gives a specific resource (Google Patents database coverage), a clear verb (returns), and a precise scope: how many grants and applications are indexed per patent office/country per year across every covered authority. It cleanly distinguishes this from sibling tools such as googlepatents_search, googlepatents_recent, googlepatents_detail, and googlepatents_classification by saying it reports aggregate coverage rather than individual records.

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?

The description implicitly tells an agent to use this tool when any aggregate patent coverage count is needed, and the phrase across every authority it covers signals it needs no partitioning or filtering. However, it never explicitly says when to use it versus the other googlepatents_* tools, nor does it mention specific alternatives or exclusion cases, leaving the routing to inference from the tool family.

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