get_model_relationship

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

With readOnlyHint=true already covering the safety profile, the description adds a genuine scoping trait: it returns the raw native definition without inferring publication state or UI placement. It says nothing about behavior on a missing relationship, whether unpublished relationships are visible, or how the result shape differs between 1:N and N:N.

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?

Two short sentences, front-loaded with the primary action and followed by the scope caveat — no filler. The phrase 'cast to 1:N or N:N metadata' is slightly cryptic about what casting entails, costing a point.

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?

This is a simple read with no output schema and readOnly annotations, so the bar is moderate, but the description leaves the return shape ambiguous ('cast to ... metadata') and doesn't say what happens when the schema name doesn't resolve. Adequate, with clear gaps for an agent deciding whether the output answers its question.

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 0% and the schema exposes two mutually exclusive alias properties (schema_name/schemaName) with no required field, so the description carries the full burden. It only says 'by schema name', giving no help on the alias ambiguity, the identifier pattern, or which parameter form to pass.

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 ('Read a native relationship definition by schema name') and narrows scope to 1:N or N:N metadata, which distinguishes it from table-level tools like get_model_definition. It doesn't explicitly name create_model_relationship/update_model_relationship as the write counterparts, so the sibling differentiation is only partial.

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?

'Does not infer publication or UI placement' is a useful exclusion that steers agents away from expecting UI/publish context, but there is no positive guidance on when to prefer this over get_model_definition or the create/update relationship tools. Usage is implied from the verb and resource rather than stated.

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