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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), and the description adds genuinely new behavioral facts: default ordering is highest search volume first, results are paginated at most 100 rows per page, and the default result set is silently narrowed to CORE. The trailing 'Read-only' restates the annotation rather than adding to it, so it is not a perfect score.

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?

It is front-loaded and dense: the verb, default ordering, and returned fields come first, followed by the scope rule and the pagination limit. The colon-and-semicolon packing of the field list is slightly heavy, but every clause carries information an agent needs.

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 13-parameter read tool with no output schema, the description conveys the return shape (field list), the row-count cap, the default sort, and the default filtering behavior, which is most of what a caller needs. The gaps are per-filter semantics for the remaining parameters, which the low schema coverage leaves under-documented.

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 description coverage is only 38% across 13 parameters, so the description must carry weight and does explain the highest-risk ones: scope's core/all semantics, the excluded_reason/geo_flag meaning ('why a keyword was set aside'), and the default ordering. However, filters such as lang, intent, search, min_volume, cluster_id, unclustered, and ordering overrides are left entirely to their enum values or names, leaving real ambiguity about how they combine.

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 opens with a specific verb and resource ('Page through a project's keywords') and enumerates the returned fields, so the agent immediately knows this is a paginated keyword listing rather than a cluster, project, or cluster-detail tool like its siblings. The default CORE-vs-all scoping further pins down what 'keywords' means here.

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?

It gives explicit guidance on the key branching decision: the default returns only CORE rows (kept, project language, not another city/country), and 'pass scope=\'all\' for everything collected' tells the agent when to switch modes. What's missing is any statement of when to prefer a different tool (e.g. seo_list_clusters for cluster-level views), so it stops short of full when/when-not/alternatives coverage.

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