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

Well beyond annotations (which only flag destructive/openWorld/non-idempotent): it warns that daily_budget on a lifetime campaign irreversibly switches budget type, that geos rewrite the whole targeting block with audiences/platforms read back unchanged, that the objective can never change, and that a dry run shows current vs proposed values. This is exactly the destructive-behavior context an agent needs.

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?

Dense but front-loaded with the verb/resource, then grouped by concern (budget, geo, platforms, dates, conversion, status, dry run). Nearly every sentence carries operational value; a few clauses (e.g. the Istanbul id example) are slightly verbose but still illustrative.

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 16-param destructive mutation with a 0%-coverage schema, the description plus an existing output schema and safety annotations leave nothing critical unaddressed: budget constraints, targeting side effects, irreversible operations, and the dry-run escape hatch are all documented.

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 coverage is 0%, so the description must carry all parameter meaning, and it does for the hard cases: budget-type exclusivity, ISO codes/geo ids for include/exclude_locations, locations_mode values with defaults, platform enum values and ['all'], date formats/time zone, and conversion_mode add/replace/remove. Only account, description, and name are left to inference.

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 (Changes/Update) and resource (existing ChatGPT Ads campaign) and enumerates the mutable surface: name, budget, locations, platforms, schedule, conversion events, status. It also implicitly differentiates from create_chatgpt_ads_campaign and update_chatgpt_ads_ad/ad_group by scoping to campaign-level 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 strong contextual guidance: 'Only what you pass changes,' confirm=false for a dry run, conversion_event_setting_ids refused on conversions-objective campaigns, and explicitly routes archiving to chatgpt_ads_status and location ids to chatgpt_ads_geo_lookup. It lacks an explicit statement of when to prefer this tool over a sibling update tool, but the routing hints are substantive.

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