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

No annotations are provided, so the description carries the full burden. It discloses that the operation runs Google validate-only and returns a before/after draft, with no change applied. This is a clear behavioral statement about side effects (none). However, it doesn't cover what happens on validation failure, whether a draft object is persisted, or any authentication prerequisites. Given the absence of annotations, this is adequate but not exhaustive.

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?

The description is a single, efficient sentence that front-loads the purpose and the key behavioral trait (no change applied). It contains zero fluff and every word adds value. It is appropriately sized for the high-level purpose, though it sacrifices parameter detail for brevity.

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 the complexity (12 parameters, multiple entity types, no output schema, no annotations), the description is severely incomplete. It does not explain how entity_level determines which fields are valid, what the before/after draft contains, or how to interpret the response. An agent would struggle to correctly select parameters for a given entity type. The description covers only the high-level flow, missing essential operational details.

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?

The schema has 12 parameters but only 8% description coverage (just customer_id has a description). The description adds nothing about parameters—it doesn't explain which parameters apply to which entity_level, nor the relationships between IDs (e.g., campaign_id for campaign, ad_group_id for ad_group, criterion_id for keyword). With such low schema coverage, the description must compensate, but it fails entirely. This is a critical gap for a tool with many parameters.

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 clearly states the tool prepares updates for four specific entity types (campaign, ad-group, responsive-search-ad, keyword), which is a precise verb+resource pairing. It also distinguishes itself by noting it runs validate-only and returns a before/after draft, setting it apart from create or confirm tools. This is unambiguous and immediately tells an agent what the tool does.

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?

The description implies usage context: it is for preparing updates (not creating) and explicitly states no change is applied, which signals that a subsequent confirm step is required. It doesn't explicitly name alternative tools, but the 'prepare' prefix and the dry-run nature clearly differentiate it from confirm and create siblings. A more explicit exclusion (e.g., 'not for creation or confirmation') would make it perfect.

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