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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the description only needs to add context. 'Always PAUSED' does exactly that: it tells the agent the campaign will not spend money until a separate enable step, which directly shapes follow-up planning. It omits account-resolution behavior and any confirmation/idempotency notes, keeping it below a 5.

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, front-loaded with the core action and resource, with the constraint list compressed into one parenthetical chain. The only inefficiency is density: the inline field enumeration plus numeric limits is a lot to parse in one sentence, 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 14-parameter mutation with no output schema, the definition covers what gets built and the paused state but says nothing about what is returned (e.g., a campaign resource ID) that the agent would need for a subsequent enable or update call. It also doesn't address multi-account selection, which matters given the openWorldHint=true annotation.

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 only 29% across 14 parameters, so the description must carry the load; it enumerates most fields (budget, target CPI, locations, languages, headlines, descriptions, images, YouTube videos, store, goal) but adds little semantics beyond naming them. The '(≤30)' and '(≤90)' notations read as character limits for headlines/descriptions while the schema declares maxItems=5, creating genuine ambiguity about whether 30 and 90 are character caps or array counts.

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+resource (create an App campaign) and scopes it to app installs or in-app actions across Google Play / App Store, which implicitly separates it from the create_search_campaign, create_display_campaign, create_pmax_campaign and create_demandgen_campaign siblings. It stops short of explicitly naming those alternatives, so the differentiation must be inferred from the campaign-type label.

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 implied rather than stated: 'Create an App campaign for app installs (or in-app actions)' tells the agent what scenario fits, but there is no explicit 'use this instead of X when Y' guidance. 'Always PAUSED' hints at a follow-up step (enabling the campaign) but doesn't name google_ads_enable_campaign or explain prerequisites such as which account is targeted.

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