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

Annotations only declare readOnlyHint=false, destructiveHint=false and openWorldHint=true. The description adds genuinely useful context beyond that: the campaign is created paused, no spend can start without the client, and the mechanism varies between an API call and a browser task. The one gap is that it never says whether an in-progress browser task must be polled or claimed later.

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?

One dense sentence that front-loads the action, the paused state, and the safety guarantee, with no filler. The all-caps emphasis on 'EN PAUSE' is slightly unusual but does draw attention to the most consequential fact.

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?

The description covers state and execution mechanism well for a one-parameter tool with no output schema, but it leaves the parameter meaning and the expected outcome (a campaign record? a queued browser task?) unexplained. For an open-world creation tool that may hand off to a browser, that is a meaningful omission.

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, 'id', with 0% schema description coverage, so the description carries the full burden of explaining it — and it says nothing. An agent cannot tell whether 'id' identifies a client, a campaign plan, a project, or an ad account, which is a real risk of passing the wrong value.

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 states a specific verb and resource ('Créer la campagne publicitaire') and adds a key qualifier ('EN PAUSE'), which immediately separates it from check_ad_campaign and subscribe_to_campaign. What it does not do is explicitly name a sibling or state the boundary against them, so it stops short of a 5.

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 describes the execution path — Meta API when the ad network is connected, otherwise a browser task in the ads manager — which tells the agent what will happen but not when a caller should choose this tool over alternatives. There are no explicit when-not conditions or sibling routing beyond the connection-state branch.

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