add_negative_keywords

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

With no annotations, the description carries the burden and does well: it discloses the two-phase preview/confirm mechanism, the role of confirm_token, and the safety guarantee that negatives only reduce spend. It does not cover permissions or side effects on existing negatives, but the core behavioral traits are clearly explained.

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?

The description is efficiently structured: a one-line purpose, a safety note, and an enumerated Args section. Every sentence is informative with no redundancy, making it easy to scan.

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?

The two-phase workflow and parameter semantics are well covered, and an output schema exists so return values are not required in the description. A minor gap is that it doesn't explicitly state the preview response returns a confirm_token, though this is implied by 'Token from the preview call. Omit for a preview.'

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?

All five parameters are documented in the Args block with meaningful descriptions (e.g., 'Terms to exclude', 'Token from the preview call. Omit for a preview.'), adding substantial value over the bare schema types/defaults. With 0% schema description coverage, this fully compensates.

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 first sentence 'Add campaign-level negative keywords' uses a specific verb and resource, clearly stating the tool's function and scope. It does not explicitly distinguish from sibling apply_negative_keyword_list, but 'campaign-level' narrows the context, so it's clear but not fully differentiated.

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?

The description implies when to use the tool by naming the target resource and describing the two-phase flow, but it does not mention alternatives, exclusions, or when not to use it. The safety note 'safest write operation' provides context but not explicit usage guidance.

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