ads_negatives_update

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

With no annotations provided, the description carries the full burden of disclosure and does so excellently. It reveals the dry-run default, the guard that refuses the batch if a negative would block traffic, the rationale (silent traffic loss), and that terms are read back. It also clarifies the consequence of a wrong negative, which is critical behavioral context beyond the schema.

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 two sentences with no wasted words. It front-loads the core purpose, then immediately provides the most important behavioral guard, and finishes with dry-run and read-back behavior. Every clause earns its place and the density is appropriate for the complexity.

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 complex 7-parameter tool with no annotations and an output schema, the description covers most key behavioral nuances: guard, dry-run, read-back, and the enumerated-list constraint. The notable gap is that it says the batch is 'refused if one would block traffic' without mentioning that confirm can override the guard, which is a significant behavioral path. The schema covers confirm, but the description's narrative is slightly incomplete on that interaction.

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 100%, so the baseline is 3, and the description adds meaningful operational meaning to several parameters: keywords are explicitly enumerated with no pattern form, dryRun's default behavior is stated, and the guard logic clarifies action and confirm's context. It does not systematically walk through each parameter but enhances the schema descriptions with non-obvious implications.

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 states a specific verb-resource pair ('Add or remove negative keywords in a batch') and adds a distinguishing constraint ('enumerated one by one with no pattern form'). It clearly differentiates from siblings like ads_negatives (which likely reads negatives) and ads_keyword_create (single keyword creation), so an agent can tell it apart without opening schemas.

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 usage context (batch operations, no patterns) but never explicitly says when to use this tool over alternatives like ads_update_batch or ads_keyword_create. It does not name any sibling or exclusion condition, leaving the agent to infer the appropriate choice from the name and purpose alone.

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