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

Annotations are absent, so the description carries the burden. It clearly signals a read-only, non-mutating assessment (returns green/yellow/red and reasons) and names the output fields. What it does not disclose: whether the call requires an existing open position, whether it triggers any side effects (e.g., logging or alerts), and what happens if positionId is invalid or stale. That is a meaningful but not critical gap for a read-style tool.

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 sentences, no filler, key output fields and the parameter covered without elaboration. The information-dense format maximizes signal per token for an agent.

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 is complete enough for a minimal call when the agent already has a positionId and understands that a threat-level read is non-mutating. Given there is no output schema and no annotations, saying what it does NOT do (no side effects, no guarantee of position existence) and where positionId comes from would tighten the contract. But for the tool's narrow scope, the gap is acceptable.

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 0%, so the description must explain positionId. It does, albeit briefly: positionId identifies the position whose threat level is assessed. It does not specify the id format (numeric vs. string uuid) or the source from which an agent would obtain it (e.g., from position list vs. close_position response). Still, for a single-parameter tool the description provides the essential semantic tie from the param to the tool's purpose.

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 specific action (get threat level) and resource (a position), and then specifies exactly what output fields the report returns: GREEN/YELLOW/RED, liq distance %, basis deviation %, reasons, recommended action. It names the single required parameter positionId. This disambiguates the tool from siblings like get_agent_events or get_basis_signal 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?

The description implies a use case: when you need a quick risk snapshot of a position. But it does not say explicitly which sibling tools are alternatives, when to use analyze_pair_liquidity or get_basis_regime instead, or any exclusion conditions. Useful but incomplete guidance on selecting it over siblings. With no usage-guidance convention in the schema or annotations unburdening it, a 3 is fair.

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