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

Annotations already carry the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), and the description adds genuine behavioral context beyond that: the data is scoped to the latest completed audit, `limit` caps only the per-prompt rows while 'probeSummary always covers the full battery', and the probeSummary/serpSummary contrast explains the data's dual source (AI probe battery vs Google SERP mirror). No contradiction with 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 primary purpose is front-loaded in the first clause, and all subsequent detail about probeSummary, serpSummary, and limit behavior is useful rather than padding. The cost is a single long sentence with nested parentheticals that is denser to parse than ideal, but no element is wasted and the length is justified by the complexity of the return payload.

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 full burden of explaining return values and does so thoroughly, enumerating probeSummary fields (per-engine totals, mention types, top competitors), serpSummary fields (top-10 presence, top-3 count, snippet ownership), and per-row contents. Remaining gaps: `workspaceId` semantics are unexplained, the no-completed-audit-yet edge case is unaddressed, and the overlap with campaignstack_seo_get_latest_report is unresolved.

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 50%: `limit` is documented in the schema, but `workspaceId` has no schema description. The tool description reinforces limit's default/max and adds the 'per-prompt × per-engine' framing that clarifies what the limit applies to, slightly exceeding the schema. However, it adds nothing about `workspaceId`, which remains undocumented in both the schema and the description, so the description does not fully compensate for the coverage gap.

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 states a specific verb and resource: 'Get AI-visibility probe results from the latest completed audit', and concretizes it by enumerating the payload sections (probeSummary, serpSummary, per-prompt rows with classification, positions, competitors, citations). This is clearly a read operation for visibility probe data, distinct from the many create/update/list siblings. It stops short of a 5 because it never names or contrasts an overlapping sibling such as campaignstack_seo_get_latest_report or campaignstack_seo_get_advisory, leaving some boundary inference to the agent.

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 recency qualifier 'from the latest completed audit' implies the tool only applies to the most recently finished audit, and the level of payload detail implies it serves visibility-analysis queries. However, there is no explicit when-to-use/when-not-to-use guidance and no alternative tools are named. The agent must infer the boundary against campaignstack_seo_get_latest_report, campaignstack_seo_get_advisory, and campaignstack_seo_run_audit on its own.

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