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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered; the description adds real context beyond that by disclosing the pre-send verification checks (operation kind, approval integrity, state drift) and the no-replay reconciliation policy. It stops short of describing failure/error surfaces or permission requirements, so not a full 5.

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, front-loaded sentences with no wasted clauses; the approval precondition and draft requirement lead. The final reconciliation sentence is slightly terse/jargon-heavy but still earns its place.

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?

For a destructive, confirm-stage mutation with no output schema, the description supplies the workflow prerequisite, the verification behavior, and the uncertain-outcome policy. The remaining gap is parameter-level detail (connection_context) and explicit failure semantics, which is a modest shortfall rather than a blocking one.

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 only 33% — customer_id is documented in the schema, but draft_id and connection_context are undocumented there. The description hints at draft_id's provenance ('a matching draft from ..._halt_prepare') but adds nothing about connection_context, so it only partially compensates for the coverage gap.

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 (halt) plus the exact resource scope (an enabled Search or Display experiment), and the precondition (after explicit approval). It is immediately distinguishable from google_ads_experiment_halt_prepare, which is the paired draft-producing sibling.

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 gates usage on prior approval and on 'a matching draft from google_ads_experiment_halt_prepare', naming the required predecessor tool. It also tells the agent what to do when the outcome is uncertain (reconcile, do not replay), covering the main alternative path.

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