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

Annotations already declare readOnlyHint=true, but the description adds real value beyond them: the switch lives in the Google Ads UI and the API exposes it read-only, so this tool only reports state while the interface mutates it, and the flag is invisible from the tag itself. This explains mutation locus and a diagnostic gotcha not derivable from annotations.

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?

The main purpose is front-loaded in the first sentence, but the description runs four paragraphs for a one-parameter read tool and reads partly like end-user documentation (UI navigation paths, the enhanced-conversions explanation). The content is relevant but overlength for its invocation purpose.

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 values need no prose, yet the description still usefully names the key fields and the account block. Combined with the read-only and diagnostic context, an agent has enough to select and call it correctly; only the sole input parameter is left undocumented.

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 0% and the description never mentions customer_id or its format. However, with only a single, self-evident identifier parameter, there is little meaning to compensate for, so this lands at the adequate baseline rather than being penalized heavily.

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 (reads) and resource (settings detail of conversion actions) and enumerates the fields returned (id, category, counting type, lookback window, attribution model, value/currency, primary flag) plus the account-level block. It explicitly differentiates itself from siblings by noting get_conversion_tags only returns the tag and that it answers what set_call_reporting cannot.

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 concrete when-to-use conditions: check the enhanced-conversions-for-leads flag when the tag sends hashed data but Google ignores it, and check call_reporting before switching it on and read it before changing it. Alternatives (set_call_reporting, get_conversion_tags) are named, though guidance is scoped to the two account sub-sections rather than the whole tool.

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