link_records

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

With no annotations provided, the description carries the behavioral burden, and it does so well: it discloses the REVIEW_REQUIRED result, the idempotent 'return the existing triple' behavior, the audit side effect, and the legacy status. It does not explain what triggers REVIEW_REQUIRED or what the audit entails, but the key surprises are surfaced.

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?

Four short sentences, all of which carry distinct value: legacy warning, action definition, evidence criterion, and audit side effect. The most important caveat is front-loaded, and there is no filler.

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 simple 3-parameter tool with an output schema, the description covers legacy/replacement routing, idempotency, evidence constraints, and audit behavior, which is strong. It would be complete with a brief clarification of REVIEW_REQUIRED implications or permission requirements, but those are not fatal gaps given the output schema and the explicit alternative.

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?

Input schema coverage is 0% and no parameter descriptions exist, so the description must compensate. 'Directed typed link' and 'active records' add meaning to source_id/target_id/relationship_type, and the idempotency behavior helps interpret what happens when a triple already exists. However, it never explicitly maps each parameter to its value rules or formats, so the compensation is only partial.

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 names a specific resource ('directed typed link'), a concrete action ('Create'), and a fallback outcome ('or return the existing triple'), with scope ('between active records in this workspace'). It clearly separates this from the prepare_write/commit_write workflow and sibling unlink_records.

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 explicitly directs agents to 'use prepare_write/commit_write' and warns that this legacy direct write 'returns REVIEW_REQUIRED', which is strong alternative guidance. The sentence 'Only explicit contextual evidence justifies a link' adds a semantic eligibility condition, though it doesn't enumerate exactly when to prefer link_records over the modern path beyond the legacy caveat.

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