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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, but the description adds real value beyond them: mutation modes (validate_only, preview_only, execute), the partial-failure policy (completed_items_not_rolled_back), synchronous execution, and the deterministic retry-key derivation. The seat-authorisation requirement for writes is genuinely useful operational context. It stops short of 5 because much of the remaining text is generic output-formatting boilerplate rather than tool behavior.

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?

It opens with the classification facts, which is well front-loaded, but is then padded with a long block of generic presentation instructions ('use assistantSummary first', 'never display raw JSON') that applies to every tool rather than this one. That boilerplate crowds out the tool-specific information an agent actually needs.

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 values need not be explained, and the description does cover the safety/precondition profile for a destructive mutation. However, for a 24-parameter nested-schema write with 0% parameter documentation and no optimistic-concurrency guidance for expectedVersion, it is not complete enough to invoke confidently without guesswork.

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 24 parameters, so the description carries the full explanatory burden, yet it only addresses idempotencyKey and seatId/seatName. The two required parameters (accountId, advertiserId) are unexplained, and expectedVersion, dryRun, and the many locale/market parameters have no semantics at all; notably the relationship between dryRun and the advertised mutation modes is never stated.

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 restates the title ('archive advertiser') and adds classification metadata ('writes to Studio, destructive'), which tells the agent this is a destructive write, but it never explains what archiving an advertiser actually does (hard delete, soft hide, cascade to campaigns/creatives) or how it differs from update_advertiser or delete_flight. The verb+resource is identifiable, so it is not pure tautology, but the semantics are left implicit.

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 when-to-use or when-not-to-use guidance relative to the many sibling mutation tools (update_advertiser, archive_campaign, archive_creative). The only selection-relevant content is a precondition ('when more than one seat is authorised, seatId or seatName must be supplied') and the idempotency-key default, which are prerequisites rather than routing guidance.

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