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

Strong behavioral disclosure: synchronous execution, mutation modes (validate_only, preview_only, execute), partial-failure policy 'completed_items_not_rolled_back', idempotency-key derivation, and the seatId/seatName requirement on multi-seat writes. These go well beyond the annotations, which only declare readOnly=false, idempotent=true, destructive=false. The main gap is that it doesn't say which permissions or account scoping are required, and 'Studio' is undefined.

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?

Behavioral facts are front-loaded (classification, execution, mutation modes, failure policy), which is good. But the response-formatting guidance about assistantSummary, raw JSON, IDs, and next-best-action is UI/prompt boilerplate rather than tool definition, and it dilutes the operative content across several sentences.

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?

Output schema exists, so return values need not be described, and the annotation safety profile is supplemented. However, a 20-parameter create tool with 0% schema coverage still lacks documentation for the advertiser object, accountId, expectedVersion, and the relationship between dryRun and the mutation modes. The description is operationally helpful but not complete enough to call blind.

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 coverage is 0% and there are 20 parameters, so the description should compensate more. It does explain idempotencyKey (auto-derivation) and the seatId/seatName requirement, which are the two most consequential params. But the advertiser object fields (name, domain, websiteUrl, status, metadata), accountId, expectedVersion, market/locale params, and dryRun vs the three mutation modes are left entirely to the bare schema.

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 'create advertiser', which restates the name/title without adding a specific verb+resource framing beyond the schema's 'advertiser' object with name, domain, status. It doesn't distinguish from sibling resolvers like leanriq_resolve_or_provision_advertiser or create_campaign. The classification 'writes to Studio' adds some scope but not purpose specificity.

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?

There is no guidance on when to use this vs alternatives such as leanriq_resolve_or_provision_advertiser (which provisions) or get_advertiser. The only usage-like statement is a seat-supply rule for multi-seat writes, which is a prerequisite, not a when-to-use decision. An agent has no routing signal among the 100+ siblings.

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