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. It does disclose the core behavior (escalating to human review), the emission of an ACM-451 event, and the return of a ticket ID for polling. However, it does not mention side effects (e.g., whether escalation is irreversible, if it blocks other operations, or what happens to the original context). It also doesn't state any permission or authentication requirements. The description is clear about the primary action but lacks depth about consequences.

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 description is two sentences, front-loaded with the core action and condition, followed by the output and next step. Every sentence earns its place: the first states what the tool does, the second explains the output and how to use it. There is no fluff or redundant phrasing, making it highly concise and well-structured.

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 tool has 5 parameters (4 required) and no output schema, so the description must clarify the return behavior. It does: it states a ticket ID is returned and directs polling via check_rfq_status. It also gives the event code (ACM-451). While it doesn't detail error handling or edge cases, for a simple escalation tool the description provides sufficient context to call it correctly and understand the outcome. The only minor gap is the absence of any mention of what to do if escalation fails, but that is not critical.

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%, meaning each parameter already has a description. The tool description does not add any extra meaning to parameters beyond what the schema provides. It only reiterates the overall purpose and output. Per the rubric, with high coverage, the baseline is 3, and the description adds no additional parameter-level insight, so a 3 is appropriate.

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 states a clear purpose: to hand a matter that cannot be resolved deterministically to human review. It specifies the verb (hand over), the resource (GSC Navigator human review), and the condition (cannot be resolved deterministically). It also mentions the output (ticket ID) and the ACM-451 event, which makes it distinct from other tools like submit_rfq or request_terms. This is a specific, actionable description that an agent can immediately understand.

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 provides a clear when-to-use condition: only when a matter cannot be resolved deterministically. This implies that for resolvable matters, other tools (e.g., submit_rfq) should be used. It also directs the agent to poll via check_rfq_status after escalation, which is an explicit next step. However, it does not explicitly list alternatives or state when not to use it beyond the deterministic caveat, so it stops short of a 5.

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