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

Beyond the annotations (readOnlyHint, openWorldHint, destructiveHint), the description adds valuable behavioral details: outputs are 'deterministic,' inputs are 'buyer-supplied' with 'explicit brands,' and it explicitly does not do 'identity resolution, source verification, browsing, or live enrichment.' It also mentions pricing and payment rail ('$0.05/call, x402 (USDC on base)'), which helps operational decision-making.

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 exceptionally concise: two sentences that front-load the core action and scope, then pack limitations and pricing into the second sentence. Every clause serves a purpose, with no redundant or filler language.

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 two-parameter tool with a rich schema and annotations, the description covers purpose, input constraints, and behavioral limits. It indicates the output type ('deterministic counts and grouped facts') but does not detail the exact structure of the return value, and there is no output schema. However, the description is sufficient for an agent to select and invoke the tool correctly in most cases.

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?

The input schema already provides 100% coverage with detailed descriptions for both parameters: rows has min/max, field descriptions, enums, and patterns; schemaVersion is a closed enum. The tool description reinforces the count limits ('1 to 60') and brand limit ('up to 15 explicit brands') already present in schema text, but it does not add new parameter-level semantics beyond what the schema specifies.

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 opens with the specific verb 'Summarize' and identifies the resource: 'buyer-supplied normalized US brand signals' for 'up to 15 explicit brands.' It clearly defines the output as 'deterministic counts and grouped facts' and distinguishes this tool from siblings by listing exclusionary traits: 'without identity resolution, source verification, browsing, or live enrichment.'

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 provides clear context on when to use the tool (with normalized buyer-supplied signals, up to 15 explicit brands) and exclusions (no identity resolution, source verification, browsing, or live enrichment), effectively telling the agent what this tool is not for. However, it does not explicitly name alternative sibling tools for those excluded capabilities, which would elevate it to a 5.

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