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

Strong extra context beyond annotations: mutation modes (validate_only, preview_only, execute), partial failure policy (completed_items_not_rolled_back), idempotency derivation when idempotencyKey is omitted, and the rule that seatId/seatName must be supplied on a write when multiple seats are authorized. These are genuinely useful and not derivable from the annotation block. One tension: it labels 'Classification: read-only' while readOnlyHint=false and mutations are described, a stated internal inconsistency that slightly undermines trust.

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 description is a wall of appended policy boilerplate (classification, execution, task support, mutation modes, output-display rules) plus a redundant duplicated sentence and double period. The meaningful content is buried and much of it reads as system-level orchestrator instructions rather than tool-selection guidance.

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?

Against 16 params and rich nested objects, an output schema covers return values so the description need not. But it leaves most input semantics undocumented and doesn't clarify the alias-vs-canonical choice, so it is only minimally adequate for a tool this complex.

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 16 parameters, so the description must carry the param burden, yet it only touches seatId/seatName and idempotencyKey. The many locale/market parameters (sourceLocale, targetMarkets, contentLocales, marketLanguageProfile, etc.) are neither described nor distinguishable, leaving the agent unable to reason about most inputs.

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 clause names a specific verb (create) and resource (campaign plan from an opportunity), which is clear. However, the definition immediately undercuts itself by identifying as a 'deprecated alias for create_creative_intelligence_plan', so the agent still cannot tell whether to call this or the canonical sibling. The purpose is stated but the deprecation muddies selection.

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 says 'Studio approval is required before campaign creation', which is one prerequisite, but gives no guidance on when to use this alias versus create_creative_intelligence_plan. Naming a deprecated alias without routing the agent to the canonical tool leaves the core selection question unanswered.

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