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

Annotations already declare destructiveHint=true and idempotentHint=true, so safety is covered. The description adds genuinely non-obvious blast-radius context: contacts are NOT deleted, only the list and its memberships are removed. That is exactly the kind of consequence detail annotations cannot express.

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 short sentences, the destructive action front-loaded and the important consequence immediately after. Nothing redundant, nothing padded.

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 simple two-parameter delete with annotations covering the safety profile and no output schema, the description supplies the one thing an agent actually needs to reason about (contacts survive, memberships don't). Return-value detail is unnecessary here; only the lack of any usage routing keeps it from a 5.

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% with only two parameters (apiKey, audienceId), both documented in the schema itself. The description adds no format, ID-source, or override detail, so the baseline 3 applies.

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+resource ('Delete an audience') and even clarifies the domain synonym ('list'), so the agent knows exactly what object is being removed. It is clearly distinguishable from create_audience/list_audiences by the verb, though it does not name a sibling explicitly the way the highest-scoring examples do.

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?

Usage is implied by the destructive verb rather than stated; there is no explicit when-to-use/when-not-to-use guidance and no pointer to adjacent tools like remove_contact_from_audience or delete_contact. The clarification that contacts survive is a useful boundary, but routing guidance is absent.

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