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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so safety is covered. The description adds genuinely new information by disclosing the three return values, which matters because there is no output schema. It does not warn about estimation cost/latency or explain the resume_id continuation behavior, which are the remaining behavioral gaps.

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 dense sentences with no filler, and the hard prerequisite is front-loaded ahead of the purpose and lifecycle context. Every clause carries actionable content.

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 read-only preview tool with no output schema, the definition covers the prerequisite skill, the intended lifecycle position, and the returned metrics. It stops short of describing the continuation flow implied by resume_id or failure/validation behavior, which would matter for a tool whose whole job is validating expressions.

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 75%, so most parameters are already documented in the schema, including the 'where' omission behavior and the resume_id instruction. The description adds only indirect meaning, tying 'where' to the create/edit cycle; it does not explain 'from', 'workspace_id', or when a resume_id round-trip occurs. 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 ('Estimates an audience's size') and then enumerates the three outputs it produces: matching row count, subject universe count, and percentage. This separates it cleanly from siblings like create_audience and update_audience, which consume rather than evaluate an expression.

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 a hard prerequisite ('MUST call `load_audience_skill` before using this tool') and a precise placement in the workflow ('during the create/edit cycle ... before calling `create_audience` / `update_audience`'). The schema further clarifies the 'where'-omitted case, so an agent knows both when to call it and when it is not yet safe to call it.

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