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

Annotations already flag destructive and open-world behavior; the description adds the meaningful non-obvious consequence that changing primary status or value perturbs automated bidding and requires confirmation. It leaves out reversibility, what HIDDEN does to historical conversion data, and partial-update semantics.

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 operations, then the risk caveat. No filler and nothing redundant.

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?

A destructive, 9-parameter mutation tool with no output schema needs more than an operation list and a confirmation warning. It omits what happens to historical data on HIDDEN, whether updates are partial or full, and what the response reports, though the schema's confirm/dry_run descriptions cover the safety mechanics.

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 coverage is only 33%, so the description does some compensating work by mapping its verbs onto name/value/counting/status/primary. However it adds no format or semantic detail for the required conversion_action_id, nor on how value interacts with currency or bidding, leaving several params undocumented in both places.

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?

Enumerates the exact updateable facets (name, value, counting, enabled/hidden status, primary/secondary) against one clearly named resource, so an agent can distinguish it from google_ads_create_conversion_action without opening the 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?

States the confirmation precondition for the two risky edits (primary status and value) because they affect automated bidding. It does not name alternatives such as create_conversion_action or pricing/conversion_performance, but the create-vs-update split is self-evident from the names.

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