update_relationship

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

Without annotations, the description carries the transparency burden. It explicitly states partial-update semantics ('Any omitted property is left unchanged') and gives exact allowed values for each behavior field. It does not mention error cases, permissions, or side effects, but the disclosed partial-update and enumeration behavior is substantial context beyond a generic 'update'.

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 dense but information-dense. It front-loads the purpose, then identification, then enumerations, and closes with partial-update semantics. While the enumeration list is lengthy, each sentence contributes useful lookup or usage details, though the run-on format slightly reduces readability.

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 12-parameter mutation tool with no output schema, the description covers the core invocation details: what to update, how to identify the target, allowed values, and partial-update behavior. It omits potential error conditions and return values, but those are less critical for this type of tool than for a read or query operation.

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?

Although the schema has high coverage (92%), the description adds crucial meaning by explaining how to combine fromTable/fromColumn/toTable/toColumn for order-insensitive identification, and it translates cardinality combinations into relationship types (1:1 / M:1 / 1:M / M:M). This goes well beyond the schema's property-level 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: 'Update an existing relationship's cardinality, filtering behaviour, active flag or join-on-date behaviour.' It clearly scopes the tool to modifying existing relationships, distinguishing it from sibling tools like add_relationship and delete_relationship.

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 clearly frames when to use this tool (to update an existing relationship) and provides identification options (by name or by the four-column tuple). However, it does not explicitly list alternative tools or state when not to use it, leaving the guidance implied rather than explicit.

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