Triage the review queue

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

Annotations already declare readOnly, idempotent, and non-destructive, so safety is covered. The description adds genuinely non-obvious behavior: under a redacted OAuth grant, lead names and draft text can be blanked and should be reported as unavailable rather than empty — a real edge case an agent would otherwise mishandle.

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 return value, then redaction caveat, then routing, then example. Every sentence carries information, though the trailing example restates what the explainTop schema entry already implies.

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?

An output schema exists, so return-format detail is not required here, and the description covers the redaction caveat plus workflow routing. Minor gap: no mention of how limit/pagination interact with the prioritized queue, which an agent triaging a long queue might need.

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 100%, so limit, explainTop, workspaceId, and workspaceSlug are already documented in the schema. The description only mildly reinforces this ('why Luca drafted what it drafted' and a sample { explainTop: 3 } call), so the baseline of 3 applies.

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?

States a specific verb and resource ('Return the coach's prioritized reply queue: pending drafts with lead context'), which is concrete enough that an agent knows exactly what comes back. It does not, however, address the near-duplicate siblings luca_review_queue_list and luca_review_queue_explain, so the distinction from those tools is left implicit.

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?

Explicitly prescribes the workflow: 'Start every review session here, then act on an item with luca_approve_and_send, luca_draft_reply, or luca_review_queue_reject.' This gives both the entry-point condition and named follow-on tools, leaving nothing to inference.

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