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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, and the description adds nothing on top. Critically, it omits the two-step behavior implied by confirm_id (a preview call returning a token, then a repeat call with the same payload to actually write), which is exactly the kind of trait the description should surface.

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 words, front-loaded, no waste — but the brevity is under-specification rather than efficiency. It cannot be called verbose, yet it also fails to earn its place with any useful content.

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 mutation tool with no output schema, an undocumented required array parameter, and a non-obvious confirmation flow, this description is far too thin. It provides no permissions, side-effect, or workflow context.

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 67%, and the description contributes zero parameter meaning. The required 'negatives' array has no description in either the schema or the description, leaving the agent without the shape or syntax of the core input.

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?

The description merely restates the tool name and the annotation title: 'Create SP negative keywords'. It states a verb and resource, but adds no distinguishing detail versus siblings such as ads_create_sp_negative_targets or ads_create_sp_keywords, which are functionally adjacent.

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?

No guidance on when to use this versus the negative-targets or positive-keyword creation tools, and no mention of the preview/confirmation workflow implied by confirm_id. The agent is left to infer everything from the name.

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