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

Annotations already declare destructiveHint=true, idempotentHint=true, and openWorldHint=true; the description adds genuine context beyond that by stating REMOVED is refused and the server never deletes, which materially reframes how the agent should treat the destructive hint. It also describes the return payload, though it omits permission/scope requirements.

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?

Front-loaded summary sentence followed by scannable Args/Returns blocks, with no filler. Slightly verbose in repeating 'Optional.' for three parameters, but it is uniformly structured and easy to parse.

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 5-parameter mutation tool with an output schema present, the description covers every input, the critical refusal behavior, and the return shape. Minor gaps remain around permission requirements and whether multiple fields can be changed in one call, but nothing needed to call it correctly is missing.

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 full burden and does so well: customer_id format (numbers only, no hyphens), ad_group_id meaning, optionality of name/status/cpc_bid_micros, the allowed status values with the REMOVED exclusion, and the unit for cpc_bid_micros (micros of the account's currency). Nothing essential is left undocumented.

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 and resource ('Updates an existing ad group's settings') and enumerates the mutable fields, so the agent knows exactly what changes. It does not explicitly distinguish itself from siblings like update_campaign or update_ad_status, but the resource naming makes the boundary inferable.

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?

There is no explicit 'use this when...' guidance versus alternatives, but the status argument carries a real usage rule: status may only be ENABLED or PAUSED because 'this server never deletes, pause instead.' That is a meaningful operating constraint embedded in parameter docs rather than a standalone when-to-use section.

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