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

Annotations already declare readOnlyHint/destructiveHint/openWorldHint, so the safety profile is covered and the trailing 'Read-only' earns no credit. The description does add genuinely new behavioral context: a hard pagination cap of 100 per page, and the fact that coverage and verification states are computed per cluster. It stops short of saying what happens on an invalid or empty project or whether results are tied to a specific analysis run.

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?

One dense but front-loaded sentence carries purpose, return shape and filter semantics, followed by two short declarative sentences for the pagination cap and read-only nature. No sentence is redundant with the name, and the most decision-relevant facts come first.

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 takes on the burden of describing return values and does so field by field, so an agent knows what it will get back. Combined with annotations covering safety and the schema covering paging and search syntax, the definition is complete for a read-only paginated list over nine parameters.

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?

At 44% schema coverage the description must compensate, and it largely does: it explains the semantics of intent, page_type (commercial page vs article), verified (Google top-10 confirmation), coverage (covered/partial/missing) and volume, which map to five of the nine parameters. The 'at most 100 per page' phrase also clarifies page_size's maximum. It adds nothing about ordering, page, or search beyond what the schema already says.

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 and resource ('Page through a project's keyword clusters') and immediately defines the unit of meaning ('one cluster is one page to have on the site'). The enumeration of returned attributes makes it clearly distinguishable from seo_list_keywords and seo_get_cluster without opening any schema.

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 'page through' and 'paginated', which signals bulk browsing rather than single-record lookup, but no alternative is named and there is no when-not guidance (e.g., use seo_get_cluster for one cluster's detail). The agent must infer the routing itself.

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