gsc_detect_cannibalization

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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior. The description adds value by stating the output is a 'review signal, not proof,' which is a useful interpretive nuance. It does not mention behavioral thresholds like minimumPages or minimumImpressions that affect results, but given the strong annotations, the additional context is adequate.

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 a single, front-loaded sentence with no redundant phrasing. Every clause adds meaning: the resource ('queries receiving impressions or clicks from multiple pages'), the temporal scope ('in the same period'), and the interpretive caveat ('review signal, not proof'). It is exemplary in conciseness.

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?

The tool has 11 parameters, three required, and no output schema, yet the description only covers the core purpose. It lacks guidance on parameter usage, output interpretation, or example scenarios. For a complex analytical tool, this description is minimally adequate but leaves gaps for proper invocation and result understanding.

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 9% (only siteUrl has a description), meaning 10 parameters are completely undocumented. The description provides no parameter semantics, failing to explain filters, dimensions, minimumPages, minimumImpressions, dataState, aggregationType, or maxRows. With such low coverage, the description needed to compensate but did not.

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 uses a specific verb 'Find' with a detailed resource: 'queries receiving impressions or clicks from multiple pages in the same period.' It immediately distinguishes this tool from sibling query tools by focusing on cannibalization detection. The caveat 'this is a review signal, not proof' further clarifies its purpose and limits.

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 implies usage for reviewing potential keyword cannibalization and sets expectations that results should be treated as signals, not definitive proof. However, it does not explicitly name alternatives or state when not to use this tool relative to siblings like gsc_query_queries or gsc_diagnose_traffic_drop. The guidance is more interpretive than directional.

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