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

Annotations declare readOnlyHint=false and destructiveHint=false, so the write aspect is already known; the description adds the crucial context that the write is to an immutable, persisted, separately confirmable plan rather than to live advertising entities. That distinction is exactly the behavioral nuance annotations cannot convey, though it stops short of describing plan lifetime, expiry, or what confirming entails.

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 sentences with the core action front-loaded and the scope exclusion last. 'Immutable, separately confirmable' is dense but earns its place because it defines the tool's contract; no filler sentences are present.

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 and scope. For a tool supporting up to 100 nested portfolio operations in a multi-step plan/confirm flow, it omits how the prepared plan is referenced later and whether partial failures leave a plan persisted.

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 reported as 0%, but the nested schema itself carries detailed descriptions for storeId format, name blankness rules, and budget policy semantics including NO_CAP and DATE_RANGE behavior. The description contributes only 'with optional budgets', adding little beyond the schema, so it neither compensates for the reported coverage gap nor harms understanding.

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 specific verb and resource: it prepares an immutable, confirmable plan that creates advertising portfolios with optional budgets. It clearly signals the prepare-vs-apply split through 'separately confirmable' and the explicit 'Does not change advertising entities' scope line, though it never names the sibling apply_portfolio_creation or prepare_portfolio_changes directly.

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?

Usage is implied rather than stated: 'separately confirmable' hints that a confirmation step follows, and 'Does not change advertising entities' excludes a misread as a live mutation. However, it does not explicitly tell the agent when to pick this over prepare_portfolio_changes or apply_portfolio_creation, nor does it name the confirmation tool.

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