find_cannibalization

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds one genuinely useful behavioral trait — that www/non-www, http/https, slash and parameter variants are reported as separate findings rather than as competing pages — but says nothing about thresholds applied, result ordering, or what a finding contains.

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 tight sentences with the core purpose front-loaded and the output-disambiguation detail second. No filler, no restatement of the tool name, and nothing an agent must read past to get the point.

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 8 parameters, no output schema, and only two annotations, the description leaves material gaps: it does not say what a returned finding looks like (query, URL list, impression shares), how results are ranked or capped by top_n, or when the data window ends. It is adequate to select the tool but thin for interpreting results.

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 75%, so most parameter meaning (site format, date windows, min_share, start_date precedence over days) is already documented in the schema. The description contributes no additional parameter semantics, and undocumented fields such as top_n and min_impressions receive no help here. Baseline 3 is appropriate given the schema already carries the load.

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?

Names a specific analytical operation on a specific resource: queries where 2+ URLs split impressions. The second sentence usefully disambiguates URL-variant duplication from real page competition, which is the key semantic distinction for this tool. It does not name a sibling (e.g. find_opportunities) to contrast against, so it stops short of a 5.

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?

Usage is only implied: an agent can infer this is a cannibalization audit for a given property, but there is no explicit 'use this when X, not Y' guidance and no mention of prerequisites such as Search Console property access or data availability windows. The clarification about variants being reported separately hints at interpretation but not invocation.

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