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

Goes beyond the annotations by disclosing partial-update semantics ('Only the fields you pass are changed'), the keep-current-bid sentinel ('leave it at 0'), and a dry-run switch ('confirm=false → dry-run'). It doesn't address reversibility, propagation delay, or permission requirements, but the destructiveHint/readOnlyHint annotations already cover the safety framing.

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?

Front-loads the action, then parameters, then safety semantics. The 'Restructuring an existing account...' sentence is longer than needed but does provide legitimate routing rationale; every other sentence is tight and load-bearing.

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?

With an output schema present, return values need no explanation, and the description covers purpose, alternatives, per-field semantics, partial-update behavior, and dry-run. Only minor operational details (permissions, latency) are missing for a mutation tool.

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 must carry the load and largely does: it defines name (new name, unique within the campaign), cpc_bid (default max CPC in account currency, 0 = unchanged), status (with the ENABLED/PAUSED enum values the schema omits), and confirm (dry-run semantics). customer_id and ad_group_id are left unexplained but are self-evident required identifiers.

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 ('Rename a Google Ads AD GROUP and/or change its default max CPC bid') and immediately scopes it against siblings, noting that update_ad_group_status handles status alone. An agent can distinguish this from create_ad_group, update_ad_group_status, and update_microsoft_ad_group without reading any 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?

Explains the motivating scenario (theme split, match type move, naming convention change) and explicitly names the alternative tool for status-only changes. The condition that selects each option is stated rather than inferred.

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