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

Annotations already carry destructiveHint=true and idempotentHint=true, so the description is not burdened with the safety profile. It still adds substantive context beyond structured data: the exact idempotent return (ok:true) and the required 'creator' scope, which no annotation conveys.

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 short sentences with the core action and its scope-of-effect front-loaded, followed by the idempotency and auth facts. No filler and nothing repeated from the title.

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?

A two-parameter mutation with an output schema, and the description covers effect boundaries, idempotency, and required scope. Return-shape details are unnecessary given the output schema, so nothing an agent needs is missing.

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 100% and both parameters are documented in-schema, so the baseline of 3 applies. The description adds no syntax, format, or ID-source guidance beyond what the schema already states.

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?

Specific verb (Remove the link) plus two named resources (audience, campaign), and the clause 'leaving the audience itself untouched' explicitly separates it from archive_audience. An agent can distinguish it from link_audience_to_campaign and the archive/patch siblings without opening a schema.

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?

Clear context for use (dissolving a campaign-audience association) and an explicit safety note that repeat calls are acceptable. It stops short of naming alternatives or stating when-not-to-use, but the 'audience untouched' clause implicitly routes destructive intent away from archive_audience.

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