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

Annotations tell the agent this is not read-only, not destructive, and not open-world, so the basic safety envelope is covered. The description adds nothing beyond that: it does not say whether 'prepare' mutates anything, produces a staged payload, expires, or requires a confirmation step — the key behavioural trait for a prepare/confirm tool.

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?

A single short sentence that is front-loaded and free of padding. It earns no penalty for bloat, but it is under-specified rather than concise, so it sits at the minimum-viable level for this dimension.

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?

Given a prepare/confirm sibling pair, 3 parameters at 33% schema coverage, and no output schema, the description is too thin. An agent cannot tell from it what the prepare call returns, whether it is idempotent, or that a confirm call is required to actually apply the recommendation.

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 33%: customer_id is documented but recommendation_resource_name and connection_context are not. The description does not compensate — it never states the expected resource-name format (e.g., customers/{id}/recommendations/{id}) or that connection_context is a context token, which is exactly the gap the description should fill.

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 verb phrase plus resource ('Prepare applying one Google Ads recommendation'), so the nominal purpose is legible. However, it does not distinguish this tool from its sibling google_ads_recommendation_apply_confirm, nor explain what the 'prepare' phase actually produces, leaving the two-phase intent implicit.

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?

No when-to-use guidance at all: no statement that this is the first half of a prepare/confirm pair, no mention that google_ads_recommendation_apply_confirm must follow, and no contrast with google_ads_recommendation_dismiss_prepare. The agent must infer the workflow from the naming convention alone.

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