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

The annotations already mark this as a non-read-only, idempotent mutation, but the description adds billable AI usage, synchronous execution, forbidden task support, mutation modes, partial failure policy, and deterministic idempotency-key derivation. These details go well beyond the annotations and are directly useful for invocation.

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 and usage are front-loaded, but the description then appends a long block of generic assistant-response instructions ('Use assistantSummary first', 'Never display raw JSON') that are not tool-specific. These sentences add noise and make it longer than necessary, though the core sections remain clear.

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 25-parameter mutation with nested objects, the description covers timing, failure policy, billing, and idempotency, which is valuable. However, it omits any guidance on required parameters and domain concepts, so an agent must guess from parameter names alone. The output schema exists, but completeness is still limited by the missing parameter semantics.

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 input schema has 25 parameters and 0% schema description coverage, so the description must carry parameter semantics. It only meaningfully explains idempotencyKey behavior ('deterministic retry key... cannot create duplicate work'), leaving required fields like objective, audience, KPI, and funnelStage unexplained. This is insufficient compensation for the low schema coverage.

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 description opens with a specific action ('Plan and create') and resource ('initial Studio creative set'), explicitly scoping to campaigns with no saved creatives. It also distinguishes from the sibling build_ad by naming it as the tool for rebuilding.

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 gives an explicit exclusion: 'Do not use this tool to rebuild existing creatives' and points to build_ad with campaignId/campaignName. The 'initial ... no saved creatives' phrase states the intended condition, making selection straightforward.

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