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

Adds substantial traits beyond the annotations: synchronous execution, task support forbidden (so no async polling), the validate_only/preview_only/execute mutation modes, and a partial failure policy of completed_items_not_rolled_back, which materially changes retry behaviour. Annotations already cover idempotency and safety, but this extra context is genuinely useful; it stops short of saying what a partial failure looks like in the response or which fields require elevated permissions.

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?

Front-loaded with classification and mutation metadata, which is good, but roughly half the text is response-formatting boilerplate (use assistantSummary, never display raw JSON, mention IDs only when useful) that is generic across the toolset rather than specific to updating an advertiser. Nothing is redundant sentence-to-sentence, but the payload-to-boilerplate ratio is poor.

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 21-parameter mutation with a nested patch object this is under-specified: the description never explains what patch does, how dryRun relates to validate_only, or how expectedVersion conflicts surface. The presence of an output schema excuses it from describing return values, but not from the parameter and semantics gaps.

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 21 parameters, so the description must carry the burden and largely does not. It explains only idempotencyKey and seatId/seatName; patch contents, advertiserId/accountId scoping, dryRun, expectedVersion optimistic concurrency, approvalId, and the market/locale parameters are all left undefined.

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?

"update advertiser. Classification: writes to Studio." restates the tool name and title without naming a single updatable field or the resource scope. Nothing distinguishes it from update_campaign, update_flight, or archive_advertiser beyond the word "update".

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?

Gives real invocation prerequisites: seatId or seatName must be supplied on this exact call when more than one seat is authorised, and idempotencyKey may be omitted because a deterministic retry key is derived. It never says when to choose this over update_campaign/archive_advertiser or when a mutation should be run as validate_only vs execute, so selection guidance is only implied.

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