kernel_agents_questions_escalate

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

With no annotations, the description carries the full burden. It does disclose the destination (a human), the expectation that the reason will be read (signalling human-facing wording), and the class of situations warranting escalation, but says nothing about what happens to the question afterwards, whether the call blocks, or what permission model applies beyond 'Chief only'.

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?

Two short sentences, front-loaded with the actor restriction, then the action, then the criteria. No redundant phrasing and nothing that could be cut without losing 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?

The core handoff is described, but for a state-changing escalation with no annotations and no output schema, the description omits the post-call effect on the question and any confirmation of what the caller receives back. Adequate to call correctly, incomplete for predicting consequences.

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%, so most parameters are already documented; the schema itself specifies the reason must be one line. The description reinforces that the reason is read by a human but adds no guidance on which question_id to supply (e.g. that it comes from the triage list) or its format.

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 object ('Hand a question in triage to the human') plus an actor restriction ('Chief only'), which cleanly separates it from sibling question tools like questions_answer and questions_triage_list. An agent can tell what this does and who may call it without opening the schema.

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 concrete trigger conditions: product or business decisions, money, irreversible actions, or uncertainty. It does not name an alternative tool or state explicit when-not conditions beyond the 'Chief only' actor restriction, so it falls short of full routing guidance.

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