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

With no annotations, the description carries the full burden and does so well: it discloses that every call hits Google live, that positions are impression-weighted rather than rank-tracker ranks, that deep positions rest on sparse data, that absolute positions are directional only, and that the response is a paginated slice whose truncated flag invalidates aggregate conclusions. These are exactly the behavioural traits an agent cannot get from structured fields.

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 purpose is front-loaded and the labelled POSITION and PAGING sections make the caveats easy to scan. It is dense but slightly overweight on pagination semantics that the schema already specifies, so a small amount of text does not earn its place.

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 5-parameter live-query tool with no annotations and no output schema, the description covers cost, metric semantics, data sparsity and pagination honesty, which is most of what an agent needs. It never describes the row contents (the competing pages/URLs and their metrics) nor the meaning of site_id, leaving a modest gap on return shape.

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 80%, so the schema already documents days, limit, offset and min_impressions including defaults and the next_offset convention. The description's PAGING block largely restates that contract rather than adding parameter meaning, so the baseline 3 is appropriate.

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?

It states a specific phenomenon — queries where two or more of the site's own pages compete and split ranking signal — which is a concrete verb+resource definition rather than a restatement of the tool name. The concept is distinct enough from siblings like Live_Content_Decay, Live_Quick_Wins and Keyword_Rankings that an agent can route to it without opening the 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?

Usable context is implied by 'Goes to Google on every call' (live, costly) and by the framing of cannibalisation as the diagnostic target, so an agent can infer when it fits. However, no sibling is named as the alternative and no explicit when-not condition is given, so guidance stays implicit rather than directive.

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