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

Goes well beyond the annotations: it discloses the dedup mechanism (account-wide CAS on request keys), the short-circuit behavior when an enabled purchase action already exists, a 15-minute preview lifetime, and an explicit list of things it does not change (upload, campaign goal, activation, budget, permissions). This materializes the idempotentHint=true and destructiveHint=false annotations into concrete, checkable behavior.

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?

Five tight sentences, front-loaded with scope, then prerequisites, then behavior, then non-effects. The telegraphic density (slashes, 'CAS', 'PURCHASE/UPLOAD_CLICKS') is efficient but assumes the reader already knows the domain jargon.

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?

With no output schema and a state-changing prepare step, the description supplies permissions, idempotency, expiry, and non-effects, which is most of what an agent needs. It stops short of describing what the preview result returns or which sibling commits it, which matters for a prepare/apply pair.

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 burden. It gives meaning to requestKey ('Account-wide CAS prevents duplicate request keys') and constrains customerId to 'the exact linked Google Ads customer', but says nothing about what 'name' identifies (the conversion action label) or any of the schema's format constraints such as the 10-digit customer ID.

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 (prepare) and a precise resource (one secondary PURCHASE/UPLOAD_CLICKS conversion action) scoped to 'the exact linked Google Ads customer', which is far more specific than the title 'Kaufaktion vorbereiten'. It does not name the sibling apply_google_ads_purchase_action, so the prepare/apply boundary must be inferred from 'Preview expires after 15 minutes'.

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 preconditions: current Owner Marketing authority plus explicit google_ads.conversion.create / ads.conversions.create rights, and states that existing enabled purchase actions are returned rather than created. It never explicitly routes the agent to apply_google_ads_purchase_action or get_google_ads_purchase_action_operation as the follow-up step, leaving the two-phase workflow only implicit.

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