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

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, so the agent knows this is a non-idempotent, non-destructive write. The description adds genuinely new behavioral context in the mandatory skill-load prerequisite, which annotations cannot convey. However, it says nothing about what is returned, whether duplicate names are rejected, or permission requirements, so it adds only partial context beyond annotations.

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?

Two sentences, zero waste, with the mandatory prerequisite front-loaded where the agent will see it. Nothing could be removed without losing information.

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?

There is no output schema, so the agent has no way to learn what a successful creation returns — critically, whether an audience id comes back for use with get_audience or preview_audience. The nested `where` predicate object is opaque and the description does not explain that it is validated or how failures surface. The skill prerequisite is covered, but the post-creation story is 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 description coverage is 83%, so the schema already documents `from`, `name`, and `where` in detail. The description contributes no parameter-level meaning beyond the resource name; the `where` predicate's dependency on the loaded skill is already stated in the schema itself. Baseline 3 is appropriate.

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 verb and resource: 'Creates a RudderStack Data Graph audience.' An agent can distinguish this from update_audience and preview_audience by the verb alone. It does not explicitly contrast itself with those siblings, so it stops short of a 5.

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 an explicit prerequisite ordering — 'MUST call `load_audience_skill` first' — and names the sibling to call first, which is the single most important routing decision for this tool. It gives no guidance on when to prefer preview_audience before creating or when update_audience is the right alternative, so it lacks exclusions.

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