Get Review Queue

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

With no annotations provided, the description carries the full burden of behavioral disclosure — and it delivers: 'Read-only; no side effects', the exact ranking order of row types, the semantics of each item_type, and the 90+ day threshold for stale_control. This is precisely the behavioral context annotations would otherwise supply.

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 structure is exemplary: purpose and read-only guarantee front-loaded, then item types, then ranking order, then follow-up routing, closing with a one-line usage directive. Each sentence earns its place, and the detail on item types is justified because each type demands a different action.

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?

The description thoroughly covers purpose, content taxonomy, ranking, and follow-up routing, and the presence of an output schema relieves it of explaining return values. The single genuine gap is the undocumented server_version parameter, which prevents full completeness for a tool an agent must invoke.

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?

The schema exposes one required parameter, server_version, with 0% schema description coverage, yet the description never mentions it. The agent is left unable to know what value to pass or how it affects the queue. The parameter name is mildly self-descriptive, but the description contributes zero compensation for the schema 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?

Opens with 'Returns the workspace's review queue: what needs a decision or a re-check, ranked' — a specific verb, a specific resource, and an explicit scope. The four item_type definitions (escalation, proposal, open_assumption, stale_control) clearly differentiate it from overlapping siblings like list_decisions, list_proposals, and get_controls.

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?

Gives an explicit entry point: 'Start here for periodic maintenance.' It also routes follow-up actions precisely — 'Escalations and proposals are decided with decide_proposal' and stale controls require verifying assertions against the codebase. The only omission is an explicit when-not-to-use contrast with list_decisions/list_proposals, but the routing is strong enough to compensate.

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