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

Annotations indicate a mutation (readOnlyHint=false) but give no deeper behavioral detail. The description adds significant context: harnesses are persistent context memory, the call can also create RIG steps, and it explains model_policy semantics including the 'required' mode refusing to run and emitting model_unavailable, plus the owner-API-key requirement for non-Haiku models. This goes well beyond the annotations.

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 first sentence is front-loaded and clear, but the second sentence is a dense run-on cramming the full RIG-step JSON structure and model_policy semantics into one long parenthetical. It is information-rich but poorly structured; splitting it into shorter, labeled sentences would improve readability without losing content.

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 thoroughly covers input semantics and edge cases for model_policy, which is the complex part of this tool. However, with no output schema, it omits what the caller should expect in return (e.g., created harness object or success confirmation). It also fails to acknowledge or resolve the harness_type enum conflict, leaving an important ambiguity for a creating tool.

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 100% and parameter descriptions are generic ('Content/value of the harness'), so the description adds real value by explaining that content is a JSON config with specific fields (skill, instruction, endpoint, tool, params, etc.) and detailing model/model_policy behavior. However, it introduces a conflict with the schema: it says harness_type can be 'skill'/'instruction' for RIG steps, while the schema enum only lists persona/preference/strategy/knowledge/compliance. This is a notable inconsistency that could mislead an agent.

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 opens with a specific verb, resource, and scope: "Create a new harness (persistent context memory) for a wallet." It also distinguishes this creation tool from siblings like update_harness, get_harness, and delete_harness by the action it performs. The additional RIG STEPS clarification further specifies what the tool can do, even though it introduces a schema mismatch.

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 when to use the tool — when creating a new harness or a RIG step — and gives detailed configuration guidance for model_policy. However, it never explicitly contrasts create_harness with update_harness or says 'use this when creating, not when modifying.' The usage context is clear enough to be inferred, but there are no explicit exclusions or alternative routing.

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