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

Annotations declare destructive/readOnly/idempotent, but the description adds substantive context beyond them: the internal lookup-then-REMOVE-mutate flow, the destructive side effect that omitting matchType removes every matching match type, and the irreversibility plus the recovery path (fresh save_campaign_draft).

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 short, front-loaded paragraphs: the action first, then the routing guidance and the irreversibility warning. No sentence is filler; each carries distinct decision-relevant information.

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 destructive tool with 3 params and no output schema, the description supplies everything needed to call it safely: what it mutates, how matchType affects blast radius, when to prefer the sibling, and that the change is irreversible with a stated recovery route.

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%, and the schema itself already documents adGroupId, matchType and keywordText, including the 'omit to remove ALL match types' semantics that the description repeats. The description adds no new syntax or format detail, so the baseline of 3 applies.

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?

States a specific verb and resource ('Remove a keyword from a live ad group') and immediately distinguishes itself from the campaign-level sibling add_negative_keywords. An agent can identify exactly what this 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?

Explicitly states the triggering condition ('when reports show a specific keyword burning budget without converting') and names the preferred alternative plus the scope difference ('to stop the whole campaign from serving on a query, prefer add_negative_keywords — removing a keyword only affects that one ad group').

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