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

Annotations already flag destructiveHint=true and idempotentHint=false, but the description adds material behavior beyond them: confirm=false triggers a dry-run, remove=true destroys the entire goal, and conversion_actions is a REMAIN-list whose omission of an id is what deletes it. This is exactly the destructive-side context an agent needs.

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 core action, then layers usage, parameter mechanics, and the dry-run note using tight arrow notation ('confirm=false → dry-run'). Every sentence carries a distinct, non-redundant instruction.

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 an output schema and full annotations exist to cover return values and the safety profile, the description fills all remaining gaps: purpose, use case, per-parameter semantics, and dry-run/destructive behavior. An agent could call this correctly and safely from the description alone.

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 the description must carry semantics, and it explains name (rename), remove (delete whole goal), conversion_actions (comma-separated ids that should REMAIN), and confirm (dry-run). Only goal_id/customer_id are left unspecified, which is acceptable since they are self-evident ids.

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 (Edits) plus a precisely scoped resource (CUSTOM conversion goal) and enumerates the three capabilities: change contained conversion actions, rename, or delete. The 'CUSTOM' qualifier implicitly distinguishes it from the sibling update_conversion_goal, so an agent can route without opening either 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?

Gives a concrete when-to-use scenario ('unblock deleting a conversion action that Google says is used by a custom goal') and a stated prerequisite ('Run list_custom_conversion_goals first to see the ids'). It stops short of naming an alternative tool or a when-not-to-use condition, which keeps it out of 5 territory.

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