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

Annotations already declare idempotentHint=true, destructiveHint=false and readOnlyHint=false, so the safety profile is partially covered. The description adds genuinely useful context beyond that: it 'creates billable AI usage,' execution is 'durable,' partial failure preserves qualified evidence, it 'never publishes or activates creative,' and a mutation with multiple authorised seats requires seatId/seatName on the exact call. Some remaining text (assistantSummary/raw-JSON output etiquette) is generic boilerplate rather than trait-specific.

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?

Purpose is front-loaded, but the first sentence duplicates the title verbatim (including a doubled period) and is followed by a long block of generic orchestration/output boilerplate. Several sentences earn their place (deprecation, billing, seat rule); others do not.

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?

An output schema exists, so return-format explanation is unnecessary. For a 9-parameter tool with deeply nested objects at 0% schema coverage, however, the description answers key operational questions (billing, durability, seat requirement) but leaves the bulk of the input model — what a 'policy' or 'routine' call vs a plain run looks like — unresolved.

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 9 top-level parameters containing deep nested objects (policy, routine, advertiserContext). The description only addresses idempotencyKey derivation and the seatId/seatName write requirement, leaving policy, routine, advertiserContext, forceRefresh, lookbackHours and routineId entirely undocumented. 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?

The opening states a specific verb and resource: 'Run bounded, current World Intelligence for one authorised advertiser,' and clarifies the output is 'source-backed external context and creative opportunities.' It also flags that this is a deprecated alias of run_world_intelligence, which is a distinguishing trait, though it never contrasts itself against get_world_intelligence or the other world-* siblings.

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 'Deprecated alias for run_world_intelligence' note implies an agent should prefer the canonical tool, and the mutation-mode list (validate_only, preview_only, execute) hints at call variants, but there is no explicit when-to-use / when-not-to-use statement or an instruction like 'use run_world_intelligence instead.' Usage is left largely to inference.

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