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

Annotations already declare readOnly/idempotent/destructive=false, and the description goes beyond them: synchronous execution, task support forbidden, and that the returned JSON is internal application state intended for orchestration. It also explains how to surface results to the user, which is real behavioral context, though it omits auth/permission requirements.

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 and the interaction guidance is useful, but the text is boilerplate-heavy, repeats the title verbatim, and contains a doubled period ('creative..'). Some sentences serve presentation policy rather than tool selection.

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 the description rightly avoids explaining return fields and instead tells the agent to lead with assistantSummary. Combined with the execution/task-support notes and safety annotations, it is largely complete, with parameter scoping as the only notable 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 description coverage is 0% with four parameters, so the description is the only source of parameter meaning. It does not explain opportunityId (required), or the seatId/seatName/advertiserId scoping logic beyond a vague 'in the selected advertiser scope', leaving the required key undocumented.

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 (Get) and a well-scoped resource (one active or historical World Intelligence opportunity plus its compact provenance) and adds a scope exclusion (does not publish creative). It is distinguishable from write/launch siblings, but it never contrasts itself with near-neighbors like get_world_intelligence or list_world_opportunities.

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 description gives response-formatting guidance (use assistantSummary, never show raw JSON) but no when-to-use/when-not guidance relative to alternatives such as list_world_opportunities or get_world_intelligence. The agent must infer that this is the single-item fetch versus the list tool.

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