cannibalization_check

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

Without annotations, the description carries the full burden of behavioral disclosure. It adds important constraints: analyze only returned data, don't speculate, and present results as rich visualizations. This goes well beyond the schema and clearly communicates expected agent behavior.

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 longer than average but well-structured with clear purpose first, then IMPORTANT and PRESENTATION sections. The instructions are purposeful and aid correct agent behavior, though the PRESENTATION block could be more concise.

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 simple two-parameter analysis tool, the description covers the objective, output specifics, and behavior constraints. There's no output schema, so the description compensates by describing what results include. Minor gap: no mention of data limits or edge cases, but overall adequate.

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?

Both parameters (days, min_impressions) are fully described in the schema with defaults, so the description adds little beyond that. The mention of 'combined impressions' aligns with min_impressions but doesn't extend the schema's semantic depth.

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?

Clearly states it finds keywords where multiple pages compete, with specific outputs (rank, position gap, impression split). This distinguishes it from sibling analysis tools like content_gaps or traffic_drops.

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 identifying internal competition but provides no explicit guidance on when to choose this tool over alternatives like content_gaps or ctr_opportunities. No mention of when not to use it.

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