remove_keyword

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the destructive nature is known. The description adds valuable behavioral context with 'confirm_removal: Must be True to proceed. Safety check,' disclosing a confirmation gate that the agent must pass to actually delete — critical because the schema default is false. It stops short of stating irreversibility or failure behavior, but the annotations carry the safety profile.

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 purpose statement is front-loaded, followed by exactly one line per argument. Roughly six lines total with zero filler; every sentence earns its place, and the safety-check note is the last item, appropriately placed with its parameter.

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 simple 4-parameter destructive operation whose safety profile is already covered by annotations, the description is essentially complete: clear action, all params explained, and the confirmation gate disclosed. The only gaps are return-value expectations and an explicit irreversibility statement, both minor given no output schema exists and the destructive hint is already set.

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 0%, so the description bears the full burden of documenting parameters, and it fully compensates: all four params receive meaningful one-line semantics (customer scope, which ad group contains the keyword, what criterion_id represents, and that confirm_removal is a mandatory safety flag). Without this text, the agent would see bare titles with no way to know the role of each ID or that confirm_removal defaults to false.

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, 'Remove a keyword from an ad group,' is a specific verb+resource statement that immediately distinguishes this tool from siblings like list_keywords, add_keywords, and update_keyword_bid, and it is clearly scope-differentiated from remove_campaign. An agent can determine what this tool does without inspecting 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?

The description offers no when-to-use guidance versus alternatives, no prerequisites, and no exclusions. The criterion_id arg implies a prior list_keywords lookup, but the description never states that flow or contrasts removal with pausing via set_ad_status.

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