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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds that results carry the 'latest verdict' along with campaign, dates, daily range, and stop rules — useful signal about returned content, especially since no output schema exists. It stops short of saying whether results are scoped, paginated, or filtered.

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?

A single compact clause with no wasted words, and the resource name is front-loaded. The colon-list form is terse but readable, though the missing verb makes it read more like a field catalog than a tool description.

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 parameterless read tool with no output schema, the description is the only place return shape can be communicated, and it partially does so. However, it never defines what a 'guardrailed budget test' is, whether the list is bounded or paginated, or how results relate to sibling tools, leaving gaps an agent would likely hit.

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 tool takes zero parameters, so there is no parameter meaning for the description to add; the rubric's baseline of 4 applies. The listed terms (campaign, dates, daily range, stop rules, latest verdict) are return-content hints, not inputs.

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 identifies the resource ('Guardrailed budget tests') and implies enumeration via the name, but uses a noun-phrase fragment rather than a verb, and gives no differentiation from siblings like list_campaigns or get_campaign. An agent can guess it lists budget tests, but the description itself mostly enumerates returned fields rather than stating the operation.

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?

There is no when-to-use guidance, no mention of alternatives (e.g., list_campaigns or get_campaign for related data), and no preconditions or exclusions. The agent must infer the tool's role purely from its name.

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