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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so safety is covered. The description adds value beyond that by disclosing the workflow role and the exact return shape (id, name, tableRef per subject), letting the agent chain straight into create_audience without guessing.

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?

Three sentences, each earning its place: what it lists, when to call it plus the required follow-up action, and what it returns. Front-loaded and free of filler.

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 thin parameter schema, the description compensates well by describing return fields and the downstream create_audience handoff. The only residual gap is the undocumented workspace_id parameter, a minor omission for an otherwise simple single-input read tool.

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?

Only one parameter (workspace_id) with 0% schema description coverage, so the description carries the burden but never explains the workspace scoping. The mention of passing an id as `from` clarifies the tool's output consumption rather than its input, so parameter semantics remain adequate but unenriched.

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 ('Lists the candidate subjects an audience can be about') and grounds it with a concrete definition ('root entities of the workspace's data graph') plus examples (Customers, Users, Accounts). This clearly separates it from siblings like list_profiles or get_audience_model_context.

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?

Explicitly positions the tool as 'the first step when authoring or exploring audiences' and tells the agent exactly what to do next: pick the matching subject and pass its id as `from` when creating an audience. It lacks explicit when-not guidance or named alternatives, which keeps it from a 5.

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