Keyword cannibalization

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

Annotations already cover readOnly/openWorld/idempotent safety, so the description only needs to add operational behavior. It does: each result lists competing pages with clicks, impressions, and position, and it implies a follow-up action (consolidate or differentiate). No contradiction with annotations.

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?

Two sentences, front-loaded with the trigger condition and ending with the output format and intended action. Every sentence earns its place; there is no filler.

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?

There is no output schema, so the description correctly takes on the job of explaining return values: competing pages plus clicks, impressions, and position. It does not mention default thresholds or result ordering, but defaults are visible in the schema and the core call pattern is clear.

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 57%, and the description adds no parameter-level guidance. It never mentions top, searchType, minImpressionsPerPage, or how filters and dates shape the analysis, leaving the agent to infer tuning from parameter names alone.

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 precise detection logic: queries for which two or more pages receive impressions, i.e. cannibalization. It uses a specific verb ('Finds') and a clear resource, and it sets the tool apart from generic analytics siblings by tying it to stuck rankings despite good content.

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 gives an explicit trigger: 'Run this when rankings look stuck despite good content.' This tells an agent when to select the tool, though it does not name alternatives or say when not to use it, so it stops short of a 5.

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