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

Annotations already declare readOnly, non-destructive, closed-world, so the safety profile is covered. The description adds substantive context the annotations cannot: unit semantics that would otherwise be ambiguous (0-100 scores vs 0-1 rates), that sub-score maxima are encoded in the keys, that quotes are verbatim from stored answers with attribution, and that a collection date is returned.

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?

Front-loads the headline metric and then works down to KPIs and perception detail, with no filler sentences. It is dense and long-winded in places, but every clause carries return-value information that has no output schema to hold it.

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 no output schema and a single trivial parameter, the description carries the full burden of describing the response — and it does so exhaustively, including key names, ranges, and the structure of the nested perception data. An agent knows exactly what it will get back.

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?

One optional parameter at 100% schema coverage, where the schema itself explains the market code format and the global-blend default. The description does not mention `market` at all, so it adds no meaning beyond the schema — baseline 3 applies.

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?

States a specific resource ('AI Visibility Score and Brand Health for this workspace') and enumerates its components with exact key names and scales. The closing 'Start here for...' line positions it as the entry-point summary, distinguishing it from the more granular siblings like get_evidence and get_rankings.

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?

Gives explicit trigger intents in quotes ('how visible are we in AI answers', 'what do AI models actually say about us') and marks itself as the starting point. It stops short of naming alternatives or stating when to skip it in favour of get_rankings or get_source_gaps.

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