preview_audience_edit

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

With no annotations, the description carries full burden for safety and side effects. It explicitly states 'Read-only helper', which communicates non-mutating behavior. It also discloses that the response is computed from the brand's current audience data, showing an understanding of context. However, it does not mention possible failure modes (e.g., invalid brandId, unparseable prompt) or the exact format of the preview, leaving some 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?

The description is two sentences, each earning its place. The first sentence states the tool's role and when to call it; the second explains the input and how to use the output. There is no fluff or repetition, and key examples of section keys are included inline.

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?

Given the absence of an output schema, the description provides a meaningful picture of the return value (available sections/subsections plus a preview) and gives concrete examples of section keys. It also explains why this tool exists (validation before edit_audience). However, the exact structure of the 'preview' and error/edge-case behavior are unspecified, leaving some completeness gaps.

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 input schema already fully describes both parameters (prompt as a natural-language string, brandId with a default). The description adds workflow context but no new parameter-level semantics. It mentions using the prompt to generate a preview and the returned keys for edit_audience, but this is about output usage, not deeper parameter meaning. With 100% schema coverage, the baseline of 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?

The description clearly states this is a read-only helper used to discover valid sections/subsections before editing the audience. It specifies a concrete action ('discover', 'returns') and distinguishes itself from the sibling tool edit_audience by explicitly referencing it. The scope is well-defined: it applies to a specific brand's audience data.

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?

The description gives explicit instructions: 'Call this BEFORE edit_audience', and explains how to pass a natural-language prompt and use the returned section keys as the required sections array for edit_audience. It clearly situates this tool in a workflow, making the recommended usage unambiguous. No competing tools are mentioned, but the sequencing and integration with edit_audience are concrete enough.

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