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

Annotations already declare readOnlyHint=false, destructiveHint=true and openWorldHint=true, so the safety profile is covered structurally. The description adds nothing behavioral on top of that: it does not say that pausing stops serving/spend, whether the change is reversible, what permissions are needed, or what the response contains. Framing it as 'activate or pause' arguably understates the destructiveHint=true annotation without contradicting it.

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?

Two short lines, with the core action and its allowed values front-loaded before the secondary workspace note. Nothing is padded. The only inefficiency is the mid-sentence language switch from the English setup to German, which adds friction rather than length.

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 described, and the annotations cover the mutation/safety profile. For a simple two-value status toggle the description is close to sufficient; the remaining gap is ad_group_id semantics (ID vs resource name) on a tool that cannot be called without it.

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%, so the description must carry the load, and it partly does: it enumerates the two allowed status values (information absent from the schema, which types status as a bare string with no enum) and explains that workspace is a customer slug that is optional when only one workspace exists. It says nothing about the format or source of ad_group_id, leaving one of three parameters undocumented.

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 names a specific verb pair (activate/pause) and a specific resource (ad group), which cleanly separates it from ads_update_ad_status, ads_update_campaign_status, ads_update_keyword_status and from ads_remove_ad_group. It also pins the value set to ENABLED or PAUSED, so the agent knows the operation is a reversible status flip rather than a delete. It stops short of explicitly naming the sibling alternatives.

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?

"Ad Group aktivieren oder pausieren" implies the use case clearly, but there is no explicit when-not guidance: nothing says whether a paused group can be re-enabled the same way, whether removed groups can be touched, or which sibling to call for bid or name changes. Usage is implied rather than stated.

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