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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=true, so the basic write/safety profile is covered. The description adds nothing on top: it doesn't explain that this is a staging-plus-confirm write, that the confirm_id is required to actually persist the change, or what happens to the inactive negatives. With annotations carrying the safety signal, the description still contributes zero behavioral context.

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?

Four words with no waste in a literal sense, but the single sentence is pure redundancy and therefore earns no place. Brevity here reflects under-specification rather than disciplined concision.

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?

This is a mutation tool with three parameters, a required undocumented array, no output schema, and an implicit preview/confirm protocol. The description covers none of the operational context an agent needs to invoke it correctly, leaving it well short of what the tool's complexity demands.

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 sits at 67%, and the description supplies no parameter meaning at all. The required 'negatives' array has no schema description and no item structure, and the description does not compensate by explaining its shape (keyword text, match type, ad group scope). The two documented params (account_id, confirm_id) are only described in 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?

The description 'Create SP negative keywords' is a verbatim restatement of the tool name and annotation title, with no added scope, target entity, or differentiation from siblings such as ads_create_sp_negative_targets or ads_create_sp_keywords. An agent cannot tell from the text which of the near-identical 'create' siblings this is beyond the name itself.

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 when-to-use guidance, no mention of prerequisites, and no reference to alternatives like ads_create_sp_negative_targets. The critical two-step flow implied by the confirm_id parameter (preview, then re-submit the same payload) is never surfaced as usage guidance.

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