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

Annotations already declare readOnly, idempotent, and non-destructive behavior, so the description's value-add is the pagination caveat and the warning that results are incomplete. That is meaningful context beyond the annotations, though it doesn't say what happens with large offsets or how the lexical labels are derived.

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?

A single dense sentence with the scoping caveat front-loaded and no filler. It is efficient, though the phrasing 'with lexical topic labels' is the only clause that slightly clouds the core statement.

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 must carry the burden of what comes back, and it does say rows plus topic labels are returned. However, for a 7-parameter tool it leaves most filter semantics and pagination behavior unexplained, which is a real gap.

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 29% across 7 parameters, and the description adds nothing per-parameter beyond the word 'paginated'. It does not explain 'area', 'days', 'direction', or how limit/offset interact, so the low-coverage gap is not compensated.

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 names a specific resource ('keyword rows for a mapped page') with lexical topic labels, which distinguishes it from siblings like read_page_connections or read_page_insights. It lacks an explicit verb, but 'All collected keyword rows' is unambiguous about what is returned.

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 sets a negative boundary ('not complete keyword discovery') and flags that results are paginated, which implies iteration, but it never names an alternative tool for full keyword discovery or explains when to prefer this versus other page reads. Usage is implied rather than prescribed.

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