agentic_interaction_trust

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 accurately describes the tool as an evidence triage mechanism, lists the return values (recommendation, signal, score, missing evidence), and clarifies that human review is required. No contradictions between description and annotations (none present).

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 a single paragraph that begins with the primary purpose, then details input and output, and ends with exclusions. Every sentence provides value, though it could be slightly more concise without losing clarity.

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?

Given the tool's complexity (one nested object parameter, no output schema), the description adequately covers what the tool does, what it requires, and what it returns. It also warns that human review is needed. It is complete enough for an agent to select and invoke the tool correctly.

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 covers 100% of the single parameter 'trust_request' with a description referencing an external schema. The description adds meaning by listing the fields within trust_request (actor, target_surface, etc.), which helps the agent understand the expected structure without needing to locate the external schema.

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 specifies the verb 'Triage' and the resource 'trust evidence for an agent-mediated interaction'. It clearly outlines the context ('before a high-stakes action executes') and lists the input structure and output components, making the tool's purpose distinct from siblings like 'analyze' or 'deep_dive'.

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 this tool ('before a high-stakes action executes') and provides exclusions: 'not cybersecurity monitoring, identity verification, or authorization'. It also notes that 'human review is required', guiding the agent to involve a human after tool use.

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