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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds real behavioral detail: what is replaced, that null clears the audience, that blocks are preserved, and that no launch occurs. It stops short of describing auth/permission requirements or the response.

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 telegraphic clauses with no filler, and the core replace/clear semantics are front-loaded. Dense and efficient, though the clipped style trades some readability for brevity.

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 destructive, revision-guarded mutation with an output schema and annotations present, the description covers the essential behaviors (replace, clear-on-null, preserve blocks, no launch). Concurrency handling is left to the schema's expectedRevision description, which is acceptable.

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 50%, with the schema documenting expectedRevision (revision/conflict) and construction inline. The description adds meaning only for the audience parameter ('null clears', 'use existing audience/tester IDs') and says nothing about construction or expectedRevision, so compensation for the coverage gap is partial.

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: 'Replace shared audience selections and participant counts', which clearly distinguishes it from create_audience, list_audiences, add_task, and set_survey. It does not explicitly name a sibling, but the resource and operation are unambiguous.

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?

'Use existing audience/tester IDs' and 'No launch' imply constraints and hint at the boundary with launch_test, but the description never states when to choose this over siblings like create_audience or set_survey. Usage is implied rather than spelled out.

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