Graph Relate

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

With only idempotentHint available, the description carries real weight and delivers: batch runs in one transaction so a DB failure keeps nothing, an invalid item is skipped and reported without blocking the rest, unknown relations degrade to RELATED_TO with the original preserved in proposed_relations, unknown types to Object with proposed_type, and re-assertion strengthens a capped edge with action 'strengthened'. These are exactly the non-obvious traits an agent needs before firing a mutation.

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?

Purpose is front-loaded and every clause carries information — no filler and no restatement of the title. It is a single dense paragraph with several stacked subordinate clauses (transaction behavior, fallback vocabulary, idempotency), which would scan better as short segments, but nothing is wasted.

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 13-parameter tool with nested batch objects and no output schema, the description covers the decision points that matter: mode selection, endpoint creation/matching, atomicity, per-item error handling, vocabulary fallbacks, and idempotent strengthening with a reported action. Return-value detail is minimized because there is no output schema to defer to, yet the one observable outcome ('strengthened') is named; the remaining batch relation-to-localId linkage stays with the schema.

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 100%, so the baseline is 3 and the schema already documents weight, relation, valid_at, provenance fields. The description adds meaning on top by grouping from_name/to_name/relation as the 'single mode' parameter set and tying the relation parameter to a required vocabulary with a documented fallback, which is more than the schema alone conveys.

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 opening sentence states a specific verb pair and resource: 'Create or strengthen a relationship between entities.' It goes further by explaining the auto-creation of missing endpoints and the match-by-name/case-insensitive/alias rule, so an agent immediately knows this is the graph write path rather than a read (graph_query) or maintenance (graph_prune) sibling.

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 splits usage into 'single mode (from_name/to_name/relation)' versus 'batch mode when extracting from a transcript or document', giving a concrete condition that selects each path. It stops short of naming sibling tools or stating when not to use this tool at all (e.g., deletion via graph_delete), so it is clear context without full routing guidance.

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