get_table_relationships

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool retrieves foreign key relationships but does not cover critical aspects such as permissions required, rate limits, error handling, or the format of returned data (e.g., list structure, included fields). This is a significant gap for a tool with no annotation support.

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 appropriately sized and front-loaded, with the core purpose stated first. The 'Args' and 'Returns' sections are structured but slightly redundant, as they repeat information from the initial sentence. Overall, it is efficient with minimal waste, though minor improvements in flow could enhance clarity.

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?

Given the lack of annotations, 0% schema description coverage, and no output schema, the description is incomplete. It fails to explain the return value format (e.g., what fields are included in the relationships list), error conditions, or dependencies on other tools like 'connect_database'. For a tool with potential complexity in database interactions, this leaves critical gaps for an AI agent.

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?

The description adds minimal semantics beyond the input schema. It notes that 'table_name' is optional and defaults to None, which the schema already indicates via 'default: null'. With 0% schema description coverage and only one parameter, the description does not compensate by explaining the parameter's role (e.g., filtering criteria) or providing examples, resulting in a baseline score.

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 clearly states the tool's purpose: 'Get foreign key relationships for a table or all tables.' It specifies the verb ('Get'), resource ('foreign key relationships'), and scope ('for a table or all tables'). However, it does not explicitly differentiate from sibling tools like 'describe_table' or 'analyze_schema', which might also provide relationship information, so it falls short of a perfect score.

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?

The description provides no guidance on when to use this tool versus alternatives. It mentions the optional 'table_name' parameter but does not specify scenarios for filtering versus retrieving all relationships, nor does it compare to sibling tools like 'describe_table' or 'analyze_schema' that might overlap in functionality. This lack of context leaves the agent uncertain about optimal usage.

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