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

Goes well beyond the annotations: guarantees the tool never deletes, defines what each allowed status does in serving terms, and discloses that over_comfort_ack is recorded locally by the hosted connector and never sent to Google. It does not mention permission scope or where the over-comfort budget threshold is read from, but the safety profile is far richer than the hints alone.

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?

Front-loaded with the one-line purpose and the no-delete constraint before the Args block. The Args/Returns list is slightly verbose for a 4-parameter tool, but each entry carries information not present in the schema.

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?

A mutation tool with 0% schema coverage needs the description to explain every parameter and the exact state effect, and it does; the return value is covered by the existing output schema. Nothing an agent needs to call it safely is missing.

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 carries the full burden and does: customer_id format (numbers only, no hyphens), campaign_id meaning, the enum-like allowed values for status, and a full explanation of the otherwise-unguessable over_comfort_ack including an example format.

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?

States a specific verb pair and resource ('Pauses or enables a Google Ads campaign') and immediately scopes it ('never deletes'). It is distinguishable from the many create_/update_ siblings, though it never names update_campaign as the place to change other fields.

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?

Gives clear when-to-use semantics: PAUSED stops serving, ENABLED switches back on, REMOVED is refused. The over_comfort_ack paragraph also tells the agent exactly when that argument applies. It omits explicit routing to an alternative tool for non-status edits.

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