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

Annotations declare destructiveHint=true, readOnlyHint=false, idempotentHint=false, so the mutation risk is already known; the description goes well beyond that by disclosing that update affects EVERY campaign using the strategy, that the strategy TYPE is immutable, that delete is refused while any campaign still uses it, that assign replaces the campaign's own bidding settings, and that confirm=false gives a dry-run preview.

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 opening sentence front-loads the core identity and the critical max/min-CPC constraint, and the action bullets are scannable. It is somewhat long and a few bullets restate the same idea (e.g. update's rename-vs-limits split), but nearly every line carries actionable detail.

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?

Given a 13-parameter mutation tool with an output schema present, the description covers identity, per-action behavior, safety guarantees, enum semantics, and dry-run. Return-value documentation is correctly omitted because the output schema handles it.

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?

With 0% schema description coverage across 13 parameters, the description carries the burden well: it maps name, strategy, max_cpc (ceiling), min_cpc (floor), target_cpa/target_roas, campaign_id, bidding_strategy_id, action values, confirm, and even enumerates the strategy enum values with currency semantics. It does not, however, explain impression_share_percent or impression_share_location, which are required to drive the TARGET_IMPRESSION_SHARE strategy it lists.

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 names a concrete resource (PORTFOLIO/shared bidding strategies in the Google Ads Shared library → Bid strategies) and enumerates each action with its own verb (list, create, create_and_assign, assign, update, delete). It explicitly differentiates itself from the sibling manage_bidding_strategies by explaining that max/min CPC limits only exist on portfolio strategies and that manage_bidding_strategies rejects max_cpc for those types.

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?

Each action carries a when-to-use cue: create_and_assign is called out as 'the usual request' with a concrete example, assign is for EXISTING strategies pulled from action=list, and delete is framed as safe cleanup for orphaned strategies. It also routes the agent to manage_bidding_strategies for moving a campaign back to its own non-shared bidding.

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