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

Annotations already declare readOnly=true, destructive=false, openWorld=false, so safety is covered. The description adds real context beyond that: that it reads *native* experiments and returns an *opaque* operation reference, warning the agent that the reference is not interpretable and must be passed back rather than parsed.

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?

A single front-loaded sentence with the read scope first and the exclusion last; no filler, no restating of the tool name.

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?

An output schema exists, so return-value explanation is unnecessary, and annotations cover safety. What remains thin is guidance on when to call it and the undocumented parameters — adequate but not fully complete for a 3-param tool with 33% schema coverage.

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% — experiment_id and connection_context carry only regex patterns, no prose. The description says nothing about any of the three parameters (customer id format, experiment id meaning, when connection_context is needed), so the coverage gap is left unmitigated.

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?

Specific verb+resource: reads experiment lifecycle, arms, and an opaque operation reference — clearly a state-read tool, distinguishable from the many experiment_*_prepare/confirm siblings. The trailing 'does not initiate or promote experiments' further bounds it, though no sibling is named 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?

The negative clause ('does not initiate or promote') implies the right sibling for those actions but never names google_ads_experiment_initiate_prepare or google_ads_experiment_promote_prepare, and no positive trigger (e.g., 'call before initiating to verify state') is given. Usage is inferable but not spelled out.

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