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

Annotations already establish the safety profile (readOnly=false, destructive=false, idempotent=false), so the bar is lower, and the description still adds genuinely useful behavior beyond them: 'confirm=false = preview, confirm=true applies' discloses a dry-run/commit gate not visible in the schema or annotations. It omits auth/permission requirements and rate-limit behavior, keeping it out of the top band.

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 dense and front-loaded, leading with the core purpose before the parameter notes, and every clause carries information (requirement, example, enum, units, preview semantics). The heavy fragment/parenthetical style is efficient but slightly telegraphic, leaving a bit of readability on the table.

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 mutation tool whose annotations carry the safety profile and which has an output schema covering return values, the description supplies the needed extras: the required dependency, key field semantics, and the confirm preview/apply behavior. Only peripheral params (account_id, customer_id) remain unaddressed, which is a minor gap.

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?

With 0% schema coverage the description must compensate, and it does for most parameters: it supplies an example for url_contains ('/products'), enumerates the operator values (Contains|Equals|BeginsWith) that the schema lacks, specifies membership_duration units (days), and explains confirm's preview/apply meaning. It leaves name, account_id, and customer_id undocumented, though these are largely self-evident.

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 remarketing audience' — and clarifies the defining trait as page-visitor (URL) based. It is far more specific than a name restatement, though it never explicitly distinguishes itself from sibling audience-creators like create_website_audience or create_customer_match_audience, relying on the tool name for that separation.

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?

Provides concrete context by flagging that uet_tag_id is REQUIRED and routing the agent to list_microsoft_uet_tags / create_microsoft_uet_tag to obtain it. It does not, however, state when to choose this audience type over the many alternative audience-creation tools, so no exclusion or alternative guidance is present.

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