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

Annotations already mark this destructive and open-world, so the description earns credit for information the annotations cannot express: which specific mutations need user confirmation, and the hard constraint that start_date cannot be set after launch. It does not state what happens if confirm is omitted or what a dry_run returns, leaving a small behavioral gap.

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 sentences, no filler. The core action is front-loaded and the confirmation rule follows immediately, with parentheticals doing compact work for the date and channel constraints.

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 9-parameter destructive mutation with a nested object and no output schema, the description covers the highest-risk facts: destructive paths require confirmation, date changes are time-bounded, and caps only apply to certain campaign types. Remaining gaps are the confirm/ dry_run contract and the frequency_cap units, both partially addressed in the schema.

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 33%, and the description only adds meaning for start_date (only before start), end_date/clear_end_date (extend or clear), and frequency_cap's channel scope. It says nothing about campaign_id, account selection, the impressions/per structure, or how confirm and dry_run interact, so half the parameters remain documented nowhere.

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 and resource ('Set a campaign's start date, end date, and an impression frequency cap') and scopes the date operation ('only before it starts') and the cap to Display/Video/Demand Gen, so an agent knows exactly what is changed. It does not name or contrast with adjacent write tools such as google_ads_update_campaign, which is the only reason it misses 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 gives concrete preconditions — start date only before the campaign starts, and explicit confirmation required for extending/clearing the end date or raising/removing a cap. It stops short of routing the agent to an alternative for other campaign fields, so a 4 rather than a 5.

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