wisdom_create_relation

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states that a relation is created, without revealing whether the relation is directional, whether source/target entities must already exist, whether duplicate relations are rejected, or whether creating relations affects downstream trust/evidence calculations. This is sparse for a mutation tool in a knowledge system.

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?

A single 13-word sentence that is front-loaded with the verb and resource. Every word earns its place, and nothing is repeated from the schema or annotations. Appropriately sized for the information it conveys.

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?

For a mutation tool with no annotations and no output schema, the description is too thin. It omits success/failure return behavior, duplicate handling, directionality semantics, and any relation to the trust/evidence features hinted at by sibling tools such as wisdom_calculate_trust and wisdom_find_contradictions. The schema covers parameters well, but the behavioral context is incomplete.

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%, so the schema already documents all four parameters plus the full relation_type enum. The description adds only marginal context by identifying fragments and tags as valid entity types for source/target. With the schema doing the heavy lifting, the baseline 3 is appropriate.

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 states a specific verb ('create') and resource ('relation between two entities'), and clarifies that entities include fragments and tags. This distinguishes it from wisdom_get_relations, its read counterpart. However, 'etc.' leaves ambiguity about which entity types are valid (e.g., can agents or projects participate?), so it falls short of full clarity.

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?

No guidance is given on when to use this tool versus alternatives. The description does not point to wisdom_get_relations for reading relations, nor does it distinguish this from wisdom_trust_agent or wisdom_link_answer, which likely create other kinds of links. An agent must infer usage entirely from the tool name and schema.

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