Read recommendations

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description goes beyond that with the authorization surface (analytics:read, luca:read, full_content sensitivity), the weekly generation cadence, dedup semantics, and the empty-list expectation. It stops short of describing pagination or response shape, but the output schema exists for that.

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-loaded with the what-it-is sentence, followed by clearly delineated operational metadata on separate lines. The empty-state sentence is the one addition that carries genuine interpretive value. Slightly more surface area than needed, but nothing is filler.

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 an output schema present, return values need not be described, and the description correctly focuses on auth scopes, workspace override, cadence and empty-state semantics. The remaining gap is routing: with dozens of analytics siblings available, the description never tells the agent which one to reach for instead.

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 67%, so the baseline is 3. The description usefully adds the default-workspace behavior and the override intent for workspaceId/workspaceSlug — a real semantic gain over the schema's terse "optional override" wording. It says nothing about weekStart or includeDismissed, which the schema also leaves undocumented, so a portion of the parameters remain opaque.

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 opening sentence gives a specific resource and scope: the coach's active prescriptive recommendations for a given week, deduped by title, generated from detected insights. An agent knows exactly what this returns. It does not explicitly distinguish itself from close siblings like luca_analytics_insights or luca_analytics_learning_insights, so a 5 is not warranted.

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 gives real interpretive guidance — an empty list is the expected, honest state and never a fabricated action — which is useful for an agent deciding whether to act. However, it never states when to prefer this tool over the many adjacent analytics siblings (insights, trends, learning_insights, objections). Usage is implied by the weekly-recommendation framing rather than addressed explicitly.

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