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

Annotations already declare destructiveHint=true and openWorldHint=true, and the description reinforces this by explaining the partial-update contract, the post-write readback ('before, after, verified'), and the conversion_campaign_locked error for conversion-optimized campaigns. It does not spell out reversibility of budget or event unlinking, but the added context goes well beyond the annotation flags.

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-loads the operation and affected fields, then breaks budget, conversion-event, status and workspace notes into short labeled lines with no filler. It is longer than a one-liner, but every line carries decision-relevant information for an agent.

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 7-parameter destructive mutation the definition covers partial-update semantics, unit conventions, error conditions, and the readback result, and an output schema exists so return structure needn't be described. The description is written in German while the tool surface is otherwise English, which is a minor friction but does not reduce correctness.

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 largely does: budgets are in account currency ('15 = 15 €/Tag') and are mutually preserving ('das jeweils andere Budget bleibt erhalten'), add_/remove_conversion_event_setting_ids are explained as attach/detach with existing associations retained, and workspace is optional for single-workspace accounts. campaign_id itself is undocumented, which is the only real gap.

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 and resource ('OpenAI-Ads-Kampagne ändern') and enumerates exactly which fields can be changed: Name, Budget, verknüpfte Conversion-Ereignisse. It also names the sibling that owns the adjacent concern ('Status: openai_ads_set_status'), so an agent can distinguish this tool from openai_ads_set_status and from the ads_update_campaign_* family without opening any schema.

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?

Explicitly scopes the tool: 'Nur angegebene Felder ändern sich' (partial update, omitted fields untouched) and routes status changes to openai_ads_set_status. It also points to openai_ads_conversion_setup as the source for conversion event IDs. It stops short of stating when an agent should prefer openai_ads_create_campaign or other update variants, so it is clear context rather than explicit when/when-not.

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