Минус-фразы кампании

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

Annotations already declare destructiveHint=true and readOnlyHint=false, yet the description adds precise destruction semantics (previous phrases are lost, empty array clears the list) and a hidden cost (add/remove perform an extra read/API call). This is exactly the kind of context annotations cannot convey.

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 with scope, then mode semantics, then the key pitfall. Three sentences, zero filler, each earning its place.

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 destructive, three-required-parameter mutation with no output schema, the description covers mode behavior, side effects, and the read-before-write implication. Nothing an agent needs to invoke it safely 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% and the enum is fully documented in the schema, so the schema carries the baseline. The description still reinforces the mode contract and adds a practical warning about replace collaterally deleting other phrases, adding value beyond the schema.

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 operation (setting negative keywords) at a specific scope (campaign level), which cleanly distinguishes it from get_campaign_negative_keywords (read) and set_ad_group_negative_keywords (ad-group scope) among the siblings. An agent can identify the right tool 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?

Explicitly enumerates when to use each mode: replace for a full swap, add to append, remove to delete named phrases. It also gives a concrete decision rule ('to add a phrase to existing ones, use add — replace with one phrase erases the rest') and states the prerequisite is unnecessary ('no need to read the list first').

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