snap_bulk_exclude_segments

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

Annotations already flag destructiveHint=true, readOnlyHint=false and idempotentHint=false, but the description adds substantial non-obvious behavior beyond them: the dry-run-by-default contract, the two-step approval_token handshake, the per-item skip rule for already-excluded squads, the batch cap, and 'stops at the first failure'. That last clause signals the operation is not atomic and that earlier items may persist, which is critical for a destructive batch mutation.

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 dense sentences, front-loaded with the operation and batch limit, then the preview/skip/failure semantics, then the confirm+token workflow. Nothing is repeated verbatim from the schema and no sentence is filler.

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, non-idempotent batch write with no output schema, the definition covers the safety flow (preview → approval_token → apply), the batch ceiling, and failure semantics. It leaves open what happens to successfully applied squads when the call stops at the first failure, and whether a retry would double-apply, which is a meaningful residual 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?

Schema coverage is only 50%: confirm and approval_token are documented in the schema, but adsquad_ids and segment_ids have no per-field description. The description compensates by clarifying that segment_ids are 'buyer-exclusion audiences' and that adsquad_ids is a set of up to 20 squads receiving the same audiences. It stops short of explaining the ID format or ordering/partial-success implications.

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+resource: 'Add the same buyer-exclusion audiences to up to 20 ad squads', which tells an agent exactly what changes and at what batch scale. It does not explicitly contrast itself with the single-squad sibling (snap_exclude_segments), so the bulk-vs-single distinction is only implied by 'up to 20 ad squads'.

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?

It gives clear operational context: default behavior is preview-only, apply requires confirm=true plus the approval_token, and squads that already exclude the audiences are skipped. It does not name an alternative tool or state when-not to use this one, which keeps it below a 5.

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