check_interaction_safety

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

With no annotations provided, the description fully handles behavioral disclosure. It states that the tool is 'read-only network call to AgentGraph API, no authentication required, no side effects.' This clearly communicates safety and operational traits beyond what annotations would provide.

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 concise at about 100 words, starting with the core purpose, then detailing return fields and usage guidance. Every sentence adds value without redundancy.

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?

Despite lacking an output schema, the description enumerates all return fields (safe, risk_level, trust_score, reasoning, recommended_action) and their types. Parameter descriptions are thorough. The tool is a simple check, and the description provides sufficient context for an agent to use it 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 input schema has 100% description coverage for both parameters (target_entity_id and interaction_type). The description adds context by explaining that interaction types have different trust thresholds (e.g., delegate requires highest trust), which complements the schema enum descriptions. This goes beyond the schema's bare details.

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 checks safety for interactions with other agents based on trust scores. It specifies return fields (safe, risk_level, trust_score, etc.) and distinguishes itself from sibling tools like check_security and check_trust_tier by focusing on interaction safety and trust thresholds.

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 recommends using this tool before delegating tasks, sending payments, or collaborating with unfamiliar agents. It also explains that different interaction types (delegate, trade, collaborate, follow) have different trust thresholds. However, it does not explicitly state when not to use it or mention alternatives, but the context of sibling tools implies appropriate use.

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