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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real value beyond them: the include_in_conversions_metric vs. misleading legacy primary_for_goal semantics, the zero-conversion alert condition, and the note that the UI 'Tracking status' diagnostic is not a single API field.

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 purpose and then layers the field-semantics caveats; every sentence is information-bearing rather than filler. It is dense and somewhat long, but the detail is justified given the confusing underlying fields.

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 not be described. Given the complexity of conversion-status semantics, the description supplies exactly the caveats needed for correct interpretation and points to the sibling for detail work, leaving no critical gap.

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%, so the description carries the burden. It explains days well ('lookback window for the conversion-volume check, default 30'), but customer_id is left undocumented in both schema and description. Partial compensation for a low-coverage schema.

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 and resource ('audits conversion actions') and immediately scopes the check to paused/removed actions and zero-data over the lookback window. It clearly differentiates itself from the sibling list_conversion_actions by naming it as the tool for the full per-action table.

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 routes the agent: 'for the full per-action table use list_conversion_actions', establishing when to use this narrow health check vs. the sibling listing tool. It also clarifies the alert logic (zero-conversion alerted ONLY for Primary/included actions), removing the main ambiguity an agent would face.

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