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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, so the safety profile is carried structurally. The description adds real value beyond that by disclosing the cost behavior ('pausing never spends money') and the execution nuance that it runs immediately subject to workspace pausing policy, which is non-obvious approval context not present in the annotations.

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 sentences, the action front-loaded ahead of the behavioral note, with no filler. The second sentence is slightly ambiguous ('if the workspace allows pausing') and could have been phrased as a concrete precondition, but nothing is wasted.

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 simple two-parameter mutation with no output schema and annotations covering the safety hints, this is close to adequate: it explains cost and execution timing. It still omits what a successful call returns, the state the campaign must be in, and any guidance on locating campaign_id, which an agent needs to invoke it reliably.

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?

With only 50% schema description coverage, the required campaign_id parameter carries no description in the schema and the description does not compensate: format, how to discover a valid ID, or what happens if an invalid one is supplied are all unspecified. Only the 'account' parameter is self-documented, so roughly half the parameter surface is left unexplained.

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?

Uses a specific verb+resource ('Pause a campaign') so the action is unambiguous at a glance. It does not, however, distinguish itself from near-siblings like google_ads_set_status, google_ads_bulk_status, or google_ads_enable_campaign, leaving the agent to infer which of these overlapping status tools to pick.

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?

Usage is only implied: the note about running immediately if the workspace allows pausing hints at an approval/permission gate but never states when to prefer this tool over google_ads_set_status for a single campaign or google_ads_bulk_status for many. No exclusions or prerequisites (e.g. campaign must be currently enabled) are given.

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