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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered, and the description adds real semantics beyond them: a 0% value means the engines never raise the brand, and when prompts span countries each topic carries `byCountry` while `country` narrows to one. The prerequisite about tracked prompts is another piece of behavior an agent cannot get from the schema.

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?

Purpose is front-loaded and most sentences carry distinct information (definition, 0% interpretation, lead-generation advice, country behavior, precondition). The 'weakest topic is usually the real content lead' sentence is advisory but earns its place by steering interpretation of the output; overall the paragraph is slightly longer than strictly needed.

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 an output schema present, the description needn't document return values, and it still covers the domain caveat, the country nuance and the workspace precondition. The only residual gap is that it never acknowledges the workspaceId/listWorkspaces friction beyond the precondition, but an agent has enough to invoke it correctly.

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 coverage is 100%, so the baseline is 3, and the description earns above baseline by explaining how `country` interacts with the response shape (`byCountry` versus 'keeps one'), which no schema field states. `scope`, `days` and `to`/`from` are left entirely to the well-written schema, which is acceptable given full coverage.

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 opening sentence names a specific verb+resource (buyer topics) and a concrete output dimension (where the brand is mentioned by AI answer engines and where it is absent). It explicitly distinguishes itself from sibling territory by stating 'This is AI visibility, not Google rankings', so an agent will not confuse it with readRankings.

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 a clear operating context ('use this before proposing anything') and an explicit precondition ('Only for a workspace that tracks its AI visibility (it has tracked prompts)'). It does not name the alternative tool an agent should call instead for traditional rankings, leaving that routing implicit through the 'not Google rankings' remark.

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