list_recent_escalations

Retrieve recent escalation events from safety audit logs to monitor self-harm and criminal intent detections. Filter by threat category and configure result limits to review critical incidents requiring immediate attention.

Instructions

Return recent escalation events from the audit log.

Parameters

limit: Maximum number of events to return (default 20). category: Filter by category ("self_harm" or "criminal_intent"). Omit for all categories.

Returns

list[dict] List of escalation records.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No
`category`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Tool Definition Quality

A3.7/5.0

Behavior3/5

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 establishes the read-only nature implicitly by describing a 'Return' operation from an 'audit log,' but fails to define the time window for 'recent' events or disclose rate limits, permission requirements, or the specific fields contained within the returned `list[dict]`.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description uses a clean docstring format with 'Parameters' and 'Returns' sections that front-load critical information without redundancy. Every line serves a distinct purpose, efficiently documenting functionality, constraints, and return type in minimal space.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple two-parameter structure and the presence of an output schema, the description adequately covers the tool's contract. The only notable gap is the undefined timeframe for 'recent' events, though the parameter documentation and return type declaration provide sufficient context for invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0% description coverage, requiring the description to provide all parameter semantics. It fully compensates by documenting both `limit` (with default value) and `category` (including the specific enum values `"self_harm"` and `"criminal_intent"` and the behavior when omitted).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool 'Return[s] recent escalation events from the audit log,' specifying the verb (return), resource (escalation events), and source (audit log). While this implicitly distinguishes it from siblings like `check_message_safety` (which likely assesses individual messages) and `get_session_risk` (which retrieves risk scores), it does not explicitly clarify when to prefer this tool over those alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no explicit guidance on when to use this tool versus its siblings (`check_message_safety`, `get_session_risk`). It lacks statements about prerequisites, such as needing audit log access permissions, or scenarios where this historical query is preferred over real-time safety checks.

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

Install Server

humane-proxy