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

Goes well beyond the annotations by disclosing billable AI usage, durable execution, the partial failure policy (completed_items_not_rolled_back), available mutation modes, deterministic idempotency-key derivation, and the hard rule that seatId/seatName must be supplied on this exact call when multiple seats are authorised. These are exactly the operational traits an agent cannot infer from readOnlyHint/idempotentHint/destructiveHint alone.

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 opening duplicates the title verbatim (with a stray double period), and the response-styling guidance (assistantSummary, never display raw JSON, mention IDs sparingly) is generic boilerplate that dilutes the tool-specific content. Useful content is present but not tightly edited.

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 complex 16-parameter, nested-object mutation with an output schema, the description covers the critical operational facts: billing impact, durability, partial-failure semantics, seat and idempotency requirements. Return values need not be explained since an output schema exists. The remaining gap is field-level guidance for the many unexplained locale/market parameters.

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 burden, and it only explains idempotencyKey (auto-derived retry key) and seatId/seatName (mandatory on the call for multi-seat writes). It says nothing about advertiserId, targetMarkets, marketContext, or the several locale parameters, so most parameters remain undocumented in both places.

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 and resource: 'Synthesize grounded, deduplicated advertiser creative opportunities from automatic competitor/category research and broad World signals,' which an agent can distinguish from retrieval siblings like get_creative_intelligence. It also flags itself as a deprecated alias for run_creative_intelligence, which is a meaningful routing signal. The wording largely mirrors the title rather than expanding on it, but the purpose is unambiguous.

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 deprecation notice ('Deprecated alias for run_creative_intelligence') tells the agent to prefer the non-alias sibling, and the explicit mutation modes (validate_only, preview_only, execute) give concrete invocation contexts. It does not state exclusions against other siblings (e.g. run_creative_chain) explicitly, so it stops short of full when/when-not guidance.

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