Draft assigning a custom conversion goal

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

Annotations already declare readOnlyHint=false and destructiveHint=false, but the description goes further: it discloses the idempotency behavior ('already_configured' when the goal is unchanged), the blast radius ('nothing else changes'), and the side effect that changing optimisation restarts the Smart Bidding learning period. This is exactly the extra behavioral context annotations cannot carry.

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-loaded with the core action and return type, then supporting constraints. Dense and mostly waste-free, though the Google Ads API link and multi-sentence constraint block are slightly more verbose than strictly needed.

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 covering the preview/plan_id return and annotations covering the safety profile, the description fills the remaining gaps: edge-case behavior, side effects, and the confirm_and_apply workflow. Nothing an agent needs to call this correctly is missing.

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%, so all three parameters are already documented with descriptions (campaign_id, customer_id default, custom_conversion_goal_id sourced from get_custom_conversion_goals). The description adds no syntax or format detail beyond the schema, 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 (assign) and resource (custom conversion goal), specifies it returns a PREVIEW, and disambiguates from siblings like draft_clear_custom_conversion_goal and draft_update_custom_conversion_goal. An agent can identify the tool's intent without opening 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 names the alternative (draft_clear_custom_conversion_goal goes back to account level), gives the precondition that triggers the tool's error (campaign must have a goal or Google answers EMPTY_CONVERSION_GOALS), and points to confirm_and_apply for applying the returned plan_id. Full when/when-not/alternative coverage.

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