get_interaction_history

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

With no annotations, the description fully discloses authentication requirements, the unsanitized nature of the context field, and the presence of context_warnings for prompt injection. These are critical behavioral traits that go beyond the basic retrieval function and help the agent handle results safely.

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 organized into logical paragraphs: purpose, filtering, use case, authentication, parameter details, and security note. Each section adds value. While it's longer than ideal, it avoids redundancy and front-loads the core functionality. Minor room for tightening, but overall well-structured.

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 the tool's purpose, filtering options, return format, authentication, and a critical security behavior. However, it lacks explicit pagination behavior beyond the limit parameter, and does not specify possible values for interaction_type or outcome. Given no output schema, it provides enough for basic usage but not exhaustive.

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 description coverage is 0%, so the description must compensate. It provides defaults and limits for 'since_days' and 'limit', which is helpful. However, it omits details for 'agent_id', 'interaction_type', 'outcome', and 'access_token' (beyond stating the need for authentication). The added information is good but incomplete, leaving agents to infer or guess for several parameters.

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 retrieves interaction history for an agent, explicitly noting filtering by type and outcome, and the return format (chronological list with timestamps, counterparty IDs, outcomes). This distinguishes it from sibling tools like agent_status or check_trust, which serve different purposes.

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 provides clear usage context ('useful for due diligence before high-value transactions') and explicitly requires authentication via access_token. While it doesn't list alternative tools or when not to use, the given context and prerequisites are sufficient for an agent to decide. No misleading guidance.

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