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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds genuinely useful non-annotation context: recommendations are computed against a per-platform baseline and refreshed every 30 minutes, which tells the agent how stale results might be. It does not disclose ordering, pagination behavior, or whether recommendation IDs from this list feed directly into apply_recommendation.

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?

Two sentences, front-loaded with the purpose and followed by supporting mechanics; no filler. The second sentence about the 30-minute sweep is useful rather than padding, but the type enumeration in sentence one is slightly 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?

A read-only list tool with fully described parameters and no output schema — the description covers what the items are, where they come from, and how fresh they are. Missing only the shape of a returned recommendation (fields, IDs) and how to act on one, which matters because the siblings apply_recommendation and dismiss_recommendation consume this output.

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%, so the baseline is 3. The description adds a little beyond the schema by framing the items as status-bearing (pending/applied/dismissed/expired are implied by the lifecycle of actionable recommendations), though it never mentions the status, launch_id, or pagination filters explicitly, so it does not earn a 5.

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 and resource ("list actionable recommendations") and enumerates the concrete recommendation types: repost/cross-post/boost winners, autopilot promote signals, underperformer pause signals. It also names the computed source (organic post performance), which distinguishes it clearly from siblings like apply_recommendation or dismiss_recommendation.

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?

Usage is implied by the noun "actionable recommendations" and by sibling pairs (apply_recommendation, dismiss_recommendation), but the description never states the when/when-not explicitly — it does not say to call this before acting on a recommendation, or point to any alternative listing tool such as list_autopilot_review.

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