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

The bracketed '[WRITE — changes your live account]' and 'Requires confirm:true' add real value beyond the annotations by flagging the safety gate and irreversibility of a live mutation. However it says nothing about duplicate handling, partial-batch failure, or error behavior for a live-account write, so it stops short of rich disclosure.

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 tight sentences: the risk tag and confirm gate are front-loaded, followed by the action. No sentence is wasted.

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 6-parameter write tool with no output schema, the description plus fully documented schema cover what an agent needs to call it correctly. Only failure/partial-success behavior for the batch mutation 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 100%, including enum values for match_type and the default for negative, so the schema carries the parameter burden. The description adds no format or interaction semantics beyond what is already documented, making baseline 3 correct.

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 (Add), resource (keywords) and target container (an ad group) with batch scope, plus the negative-keyword variant. An agent can distinguish this from sibling read/research tools like google_ads_keyword_ideas 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?

It states the mandatory precondition (confirm:true) and implies batch semantics, but never names alternatives or when-not-to-use — e.g. whether to prefer google_ads_update_ad_group or how this differs from keyword research. Usage is inferable but not routed.

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