update_model_relationship

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

Annotations only flag destructive/not-idempotent; the description goes well beyond by disclosing that table/column/intersect identity and omitted settings are preserved, that cascade changes affect future deletion, ownership and access, that native cross-relationship rules stay platform-validated, that a planHash plus explicit unprotected write are required, and that saving is separate from publication. These are exactly the operational facts an agent needs before invoking a destructive 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?

The whole definition is a single dense paragraph where every clause carries distinct information (scope, preservation, risk, gating, publication). It is front-loaded with the verb+resource, though heavy jargon like 'per-side menus' and 'full native PUT' makes it slower to parse than a short bulleted structure would.

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 11-parameter nested mutation with no output schema, the description covers the risk profile, the preview/execute contract, prerequisites and the fact that saving is distinct from publication. What remains thin is the return of the preview step and the eligibility-check details, both partially covered in schema field descriptions.

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 73%, and the description fills key gaps: it names planHash (expectedHash) as required for execution, the explicit unprotected-write flag (allowUnprotectedWrite), language merging for the label arrays, and per-side menus (entity_1_menu/entity_2_menu) for N:N. It does not explain the alias duplication or the patch/omit semantics in depth, but adds clear value beyond the schema.

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?

States a specific verb and resource: 'Preview/update an existing unmanaged custom 1:N menu/cascade or N:N per-side menus' via 'full native PUT with language merging'. The 'existing' and 'unmanaged custom' qualifiers implicitly separate it from create_model_relationship, but no sibling is named explicitly, so an agent must infer the boundary.

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 is implied rather than stated: 'Preview/update' plus the schema default dryRun=true and 'Menu must be confirmed customizable' sketch a preview-then-execute workflow with a prerequisite gate. However, the description never says when to pick this over create_model_relationship or get_model_relationship, and gives no explicit exclusions.

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