Read review queue changes

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

Annotations already cover readOnly/idempotent/non-destructive safety, and the description adds real value beyond them: the delta-since-a-cursor contract, the meaning of reload=true as a stale-version signal, the required scopes, and the workspace-override default. Missing only what happens when the cursor predates retention beyond the reload flag.

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 core delta semantics and the reload escape hatch are front-loaded in the opening two sentences, with operational metadata (scopes, idempotency, workspace override) demoted to a compact block below. Templated framing lines add slight bulk but each carries procedural information.

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, the description needn't explain return values, and the annotations cover the safety profile; what remains — the cursor model, the reload signal, scope requirements, and workspace defaults — is all present. The only gap is clarifying the 'since' value format against the schema's date-time pattern.

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 67% and the 'since' parameter has no schema description at all, so the description carries the burden there — it explains 'since' as the version a previous call returned, though it never clarifies that the value is an ISO timestamp rather than an opaque cursor token. workspaceId/workspaceSlug are already described in the schema and the description only restates the override behavior.

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 first sentence states a specific verb (read) and resource (drafts that entered/left the pending queue since a prior version), which is clearly a delta endpoint and distinguishable in kind from luca_review_queue_list. It stops short of naming the sibling it replaces or the full-list alternative, but the semantics are unambiguous.

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 reload clause implies the fallback path ('list the queue again') and the delta model implies this is for incremental polling, but neither is stated as explicit when-to-use guidance and luca_review_queue_list is never named. An agent must infer the polling workflow.

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