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

Adds real behavioral context the annotations don't carry: acknowledgement stays pending until read-only reconciliation proves completion, and timeouts must never be replayed (retry/idempotency semantics). The destructiveHint=true annotation already covers the safety profile, so this is genuine added value rather than repetition.

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 tight clauses with the core confirmation behavior front-loaded and the routing guidance last. No filler, though the compatibility note could be phrased more economically.

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?

Covers the confirmation/reconciliation model well, but as a generic compatibility dispatcher with no output schema and only 33% parameter coverage, it leaves the meaning of draft_id/connection_context and the set of valid actions unexplained. Adequate but with clear gaps.

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 description coverage is only 33% (customer_id alone is documented) and the description mentions no parameters at all, so draft_id and connection_context are undocumented in both places. With low coverage, the description was expected to compensate and does not.

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 (send) and resource (one approved experiment action), and distinguishes itself from siblings by naming the two named tools to prefer instead. The generic "experiment action" scope stays slightly vague, but the routing note gives an agent enough to tell it apart.

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 says this is a compatibility entrypoint and directs the agent to prefer google_ads_experiment_schedule_confirm or google_ads_experiment_promote_confirm. It does not spell out the residual case in which this generic tool is actually the right call, so it falls just short of a full when/when-not rubric.

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