Минус-фразы группы

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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds the concrete consequences: replace discards prior phrases, an empty array clears the list, and add/remove read the current list themselves (an extra API call). This discloses what gets destroyed and the side-effect cost beyond what annotations provide.

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?

Three sentences, front-loaded with the resource and the mandatory mode, and the most important gotcha (add vs replace) lands last. Some mode detail overlaps with the schema, costing a little density, but there is no filler.

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 3-param mutation tool with no output schema, the description covers the essential behaviors: mode requirement, destruction semantics, and the read-then-write behavior of add/remove. It omits permissions/authorization context but is otherwise sufficient to call the tool correctly.

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 mode field's schema already documents replace/add/remove semantics plus the matching/comparison rules. The description mostly reiterates the mode behavior and only adds the 'no need to read the list first' note, so it does not substantially extend the schema. Baseline 3 is appropriate.

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 ('Минус-фразы на уровне группы объявлений') and pins the scope to ad-group level, which distinguishes it from the campaign-level siblings get_campaign_negative_keywords and set_campaign_negative_keywords. An agent can tell what this does 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?

Gives clear operational guidance: mode is mandatory, each mode's effect is spelled out, and it warns that to append you must use add rather than replace (with the concrete failure mode). It does not explicitly contrast the tool against the campaign-level sibling, so tool selection is left partly to inference.

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