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

Annotations include readOnlyHint=true, and the description does not contradict that. It adds valuable behavioral context beyond the annotation by detailing what the tool returns, including specific issue codes, and by explaining the active-Space scoping and override mechanism.

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 description is front-loaded with the primary action and then packs relevant detail into three sentences. The list of issue codes is extensive but useful for an agent deciding to use the tool. Each sentence earns its place, though the first sentence is somewhat dense.

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?

With no output schema, the description carries the burden of explaining return values, and it does so thoroughly: match rate, upload failures, last-event age, issue codes, and trust line. It also covers scoping and override. It doesn't mention error cases or return format explicitly, but it's complete enough for selecting and invoking the tool.

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 100% for the single optional space_id parameter, and the schema description already explains the default and override behavior. The tool description repeats this but doesn't add significant new meaning beyond the schema, so the baseline of 3 is appropriate.

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?

The description uses a specific verb+resource ('Return conversion-loop health for the active Space') and clearly enumerates the exact outputs (per-source match rate, uploads accepted vs partial-failure, last-event age, issue codes, trust line). This distinguishes it from sibling tools like get_conversion_status or get_conversion_report by focusing on health/diagnostic state.

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 description explicitly identifies the use case as 'The "is the loop working / how confident" check', giving clear context for when to invoke it. It also explains scoping behavior and points to set_active_space as a related tool, though it doesn't explicitly mention alternatives to avoid.

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