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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, but the description adds execution semantics not present there: 'Execution: synchronous' and 'Task support: forbidden'. It also discloses output handling (returned JSON is internal state; use assistantSummary first; never display raw JSON), which is genuine behavioral context beyond structured fields.

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 first sentence is a verbatim duplicate of the title, wasting the highest-value slot. The rest is front-loaded and reasonably tight, but the classification/execution/task-support boilerplate reads as generated metadata rather than earned prose.

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 values need no explanation, and annotations plus the description cover safety and presentation behavior. The significant remaining gap is the 16 undocumented input parameters with no schema descriptions, which the description does nothing to compensate for.

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?

The schema has 16 parameters with 0% description coverage, so the description carries the full documentation burden for parameters and yet mentions none of them. Required advertiserId/runId, and the seat/market/locale fields, are entirely unexplained in prose.

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 (Read) and resource (an exact durable intelligence run) plus the payload contents (stage, terminal state, retry metadata), and explicitly names the canonical sibling get_creative_intelligence_run that it aliases. However the opening sentence is a verbatim repeat of the title, so there's a little tautology, and it doesn't distinguish itself from get_creative_intelligence or the run_* tools beyond the deprecation note.

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?

'Deprecated alias for get_creative_intelligence_run' is an explicit when-not-to-use signal that routes the agent to the canonical tool. Beyond that routing there is no positive condition for when this deprecated variant should be selected, so it stops short of the full when/when-not/alternatives treatment.

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