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

With annotations already covering readOnly/destructive/idempotent, the description goes well beyond them: it discloses that the call creates billable AI usage, runs synchronously, forbids task support, exposes validate_only/preview_only/execute mutation modes, uses a completed_items_not_rolled_back partial failure policy, and explains that an omitted idempotencyKey still yields a deterministic retry key. It also tells the agent how to present results (assistantSummary first, no raw JSON). This is unusually rich behavioral context.

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 restatement of the title, and a large fraction of the text is generic server-wide orchestration boilerplate about JSON display and summarization rather than anything specific to this tool. The deprecation fact, which is the one thing an agent most needs, is buried in sentence two behind duplicated content.

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-value explanation is not required, and the description compensates with strong execution/mutation/presentation guidance. However, for a 20-parameter mutation tool with zero schema description coverage, leaving every business parameter undocumented is a real completeness gap, and the reference to idempotencyKey (absent from the schema) adds ambiguity.

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?

Twenty parameters at 0% schema description coverage means the description carries the full burden, and it does not pay it: brand, format, objective, the nested creative object, targetMarkets, and the entire locale family are never explained. Worse, it discusses an idempotencyKey parameter that does not appear in the schema at all, and mutation modes that no property exposes, so its only parameter-adjacent content is misaligned with the actual input contract.

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 names a specific operation (QA a creative for launch readiness) and states plainly that this is a 'Deprecated alias for qa_creative', which is the single most important differentiation fact against the large sibling set. It stops short of a direct imperative ('use qa_creative instead'), but the resource, verb, and relationship to the canonical tool are all recoverable.

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 both the workflow position ('before preview, revision, or trafficking') and the routing signal ('Deprecated alias for qa_creative'), so an agent can tell where QA sits in the chain and that the canonical entry point is elsewhere. There is no explicit exclusion sentence telling the agent not to call this one, which keeps it out of 5 territory.

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