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

The annotations already declare destructiveHint=true and idempotentHint=true, so that part is redundant. What the description adds beyond them is genuinely useful: it scopes the destruction ('leaving the audience itself untouched', so destructiveHint does not mean audience deletion), states the required 'creator' scope, and confirms the ok:true return on repeat calls.

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 zero filler, and the core action is front-loaded before the safety and auth notes. Every clause carries information an agent would otherwise have to guess.

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 two-parameter unlink operation with full schema coverage, an output schema, and annotation coverage of the safety profile, the description covers action, scope of destruction, idempotency, auth, and return signal. Only edge cases such as unknown or invalid IDs are left unaddressed.

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%, so both required parameters (campaign_id and audience_id) are already documented in the schema. The description reinforces the directional relationship between the two IDs but adds no format, validation, or lookup detail beyond that, making the baseline 3 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 opens with a specific verb and resource: 'Remove the link between an audience and a campaign.' That is precise enough to separate it from link_audience_to_campaign, though it never names the inverse sibling explicitly, which is the only thing keeping it from a 5.

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 verb rather than stated. The retry safety note ('calling it again for an already-unlinked pair is safe') tells the agent when re-invocation is acceptable, but there is no explicit guidance on when to prefer this over alternatives such as archiving the audience or patching the campaign.

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