relationship

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

Annotations already carry readOnlyHint=false and destructiveHint=true, and the description is consistent with these: it lists delete actions and adds that they 'need reason', which is useful behavioral context beyond the structured fields. It does not contradict the annotations, but it stops there — no mention of consequences of deletion, idempotency, or permission requirements, so it meets but does not exceed the lowered bar.

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 a single information-dense paragraph, front-loaded with the domain phrase 'Family Tree relationships' followed by a compact action list using dot separators — every clause earns its place. It is slightly wall-of-text dense, but there is no filler and the structure effectively packages six actions plus parameter hints.

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 complex 6-action, 12-parameter dispatch tool with no output schema, the description covers the core action semantics and key constraints (required params per action, lineage types, delete reason) but leaves notable gaps: changeMessage is undocumented, the facts array structure is only glossed as 'optional marriage facts', and get actions give no hint of what they return. Adequate for basic invocation, incomplete for full agent autonomy.

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?

With schema description coverage at 0% across 12 top-level parameters, the description carries the full burden, and it compensates well: it maps person1/person2 to create_couple, child/parent1/parent2 to create_child_parents, relationshipId to the get actions, reason to deletes, and enumerates the lineage enum values (BiologicalParent/AdoptiveParent/StepParent/FosterParent/GuardianParent). It does not cover every parameter (changeMessage is absent), but the action-to-parameter mapping adds substantial meaning the bare schema lacks.

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 the resource ('Family Tree relationships') and enumerates six specific verb+resource actions (create_couple, create_child_parents, get_couple, get_child_parents, delete_couple, delete_child_parents), so an agent knows exactly what the tool operates on. However, it never distinguishes itself from the sibling 'person' tool, which is a natural alternative for family-tree data, so it misses the sibling-differentiation tier.

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?

Usage context is implied rather than explicit: the action list with its parameter hints shows which parameters are needed per action, and 'from person.get' hints at a workflow for obtaining relationship IDs. But it never states when to prefer this tool over siblings like 'person' or 'record', and gives no exclusions or alternative routing, so the guidance stays at the implied level.

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