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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the '[read-only]' prefix is redundant, but the description adds genuinely new context: the cost model ('Free'), the plan gate ('Pro plan or higher'), and the shape of returned per-CTA data. Those are behavioral facts the annotations do not carry.

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 most important information (read-only, what the resource is, the status filter) is front-loaded, followed by return shape, cost, and plan requirement. It is dense but every clause carries information; the parenthetical endpoint note and the '[read-only]' tag are the only mildly redundant parts.

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 read tool with no output schema, the description covers the resource, the filter, the returned fields, cost, and access tier. The only material gap is the handling of an omitted brandId, which the schema description partially covers and the tool description does not.

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 50%: brandId is fully documented in the schema, while status has only an enum and no description. The description mirrors the enum values and frames status as a filter, which adds modest meaning, but it does not explain brandId's defaulting behavior or what happens when it is omitted.

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 names a specific verb and resource ('the brand's CTA bank'), states the available status filter inline, and previews the returned data (goal fields, claims result). An agent can distinguish it from ctas_create, ctas_update, and ctas_generate by implication, though the siblings are never named explicitly.

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 useful preconditions — 'Free' and 'Needs the Pro plan or higher' — which help an agent decide whether the call is permissible. However, there is no explicit guidance on when to use this list versus a sibling like ctas_generate or cta_check, so the when-to-use decision is only implied.

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