Archive ad

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is partly covered. The description adds the materially important fact that the action is PERMANENT and cannot be reversed, which is exactly the disclosure an agent needs before a destructive call. It does not mention idempotency, auth requirements, or what happens to dependent entities.

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?

Three short sentences with zero waste: the action, the critical irreversibility fact in caps, and the user-confirmation instruction. The most decision-relevant information is front-loaded.

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 one-parameter mutation with no output schema and annotations covering safety hints, the description supplies the essential missing context: permanence and the need to notify the user. Only marginal items, such as what the call returns or how dependent entities are affected, are absent.

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?

There is a single required parameter (ad_id) with a documented pattern and 100% schema coverage, so the schema carries the full burden. The description adds no format, sourcing, or resolution guidance beyond it, which matches the baseline for a fully documented single-param tool.

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?

"Archive an ad" states a specific verb and resource, which is clearly distinct from create_ad, update_ad, or list_ads. It stops short of contrasting with pause_ad, which is the most plausible near-neighbor an agent could confuse it with.

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 one concrete procedural rule ("Say so to the user before calling"), which is genuinely useful pre-call guidance. However, it offers no guidance on when archiving is appropriate versus pausing the ad or archiving a parent object, leaving the main selection decision to inference.

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