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

The description adds valuable behavior beyond annotations: there is no fixed predicate vocabulary, the edge can connect any stored entity, and exact duplicate storage returns the same id rather than creating a duplicate. Annotations already signal mutating/destructive behavior, and the description does not contradict them; it enriches them with deduplication semantics.

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 longer than average, but each sentence contributes: the core action, the open vocabulary, the distinction from Lineage, and the deduplication rule. It is front-loaded with the main action and remains structured enough to parse quickly.

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 three-parameter tool with clear annotations and complete schema coverage, the description covers the important context: what counts as a Relation, how it differs from Lineage, and what happens on duplicate storage. The absence of an output schema is partially mitigated by the mention of returning the same id; a brief note on the success response shape would make it fully complete.

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 baseline is 3, but the description adds semantic meaning to the predicate parameter by emphasizing that it is caller-defined and giving examples like hasMember, cites, and supersedes. It also clarifies subject and object as endpoints of a typed edge between stored entities, which goes slightly beyond the schema's terse descriptions.

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 and resource: 'Record a typed edge between any two stored entities.' It defines the tool's scope precisely (any content-id-addressed entity) and explicitly distinguishes Relations from Lineage and from sim_create_collection's membership edges, making it clear what this tool is for.

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?

It gives concrete guidance on when to use this tool versus Lineage: Lineage is for derivation, while Relations are for any other relationship assertion. It also references datum_link as a behavioral peer and mentions membership edges, giving an agent enough context to select the right tool, though it stops short of an explicit 'use X instead' list.

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