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

Annotation coverage is low, yet the description discloses a great deal beyond it: classification (writes to Studio), execution mode (synchronous), task support (forbidden), mutation modes (validate_only, preview_only, execute), partial failure policy (completed_items_not_rolled_back), idempotency-key derivation, and the multi-seat requirement for writes. These are meaningful operational traits an agent needs and are not present in the annotations or schema.

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 purpose is front-loaded correctly, but the body is dense and partly generic output-formatting boilerplate (assistantSummary guidance, 'never display raw JSON') that does not help tool selection, and it carries a stray double period. Useful content is present but not well-separated from low-value boilerplate.

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 with an output schema (so return values need not be described) and 10 parameters, the description covers authorization, seat prerequisites, idempotency behaviour and failure semantics comprehensively. The remaining gap is the unexplained core identifiers, but the operational picture an agent needs to call it safely is largely complete.

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 0% across 10 parameters, so the description carries the full burden. It only adds meaning for seatId/seatName and idempotencyKey; the required advertiserId, campaignId and opportunityId, plus dryRun, approvalId, accountId and expectedVersion, remain undocumented anywhere. It does not compensate for the coverage gap.

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 (select), a precise resource (one reviewed, source-provenanced World Intelligence opportunity) and a target scope (authorised Studio campaign). It further distances itself from siblings by enumerating what it explicitly does not do (no feed materialisation, no creative/traffic/publish), which makes it distinguishable from list_world_opportunities, get_world_opportunity and the launch/traffick tools.

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?

The purpose implies usage but no alternative is named and no when/when-not boundary is drawn against siblings like get_world_opportunity or list_world_opportunities. It does add a real precondition (seat must be supplied on the exact call when more than one seat is authorised), which raises it above pure implication but stops short of explicit routing guidance.

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