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

With no annotations, the description carries the full burden of behavioral disclosure. It discloses that the tool packages reasoning state, routes to a human, and preserves work, but it does not describe potential side effects, whether the escalation blocks the current workflow, or what happens after routing.

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 three sentences, front-loaded with the main action, and contains no redundant content. The em-dash label is a minor stylistic choice but does not waste words.

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 covers purpose, usage, and core components, but lacks guidance on 4 of 7 parameters and does not discuss side effects or return behavior beyond the existence of an output schema. For a complex tool with no annotations and no schema descriptions, these gaps make it only partially complete.

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 has 0% description coverage, so the description must compensate. It explicitly names evidence_gathered, options_considered, and recommended_action, but does not explain the required 'question' and 'reasoning' parameters, the 'urgency' enum semantics, or 'session_id'. This partial coverage is insufficient for a 7-parameter tool.

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 clearly states the tool performs contextual escalation by packaging the full reasoning state and routing it to a human for review. It uses specific verbs ('packages', 'routes') and identifies the resource (full reasoning state), distinguishing it from sibling tools like get_escalation_recommendation.

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 explicitly states when to use: 'Use when you hit genuine uncertainty that the system cannot evaluate.' It provides clear usage context but does not mention alternatives or explicit when-not-to-use conditions.

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