tableKeys

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

The annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces this with "Reading only". It adds useful output-oriented detail about cardinality and enforcement, but it does not disclose other behavioral aspects such as errors, authentication needs, or how missing tables are handled. The description carries only some weight beyond the structured annotations.

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 compact and front-loaded: the first sentence gives the complete purpose and output composition, the second frames the use case helpfully, and the final sentence is a concise read-only reassurance. There is no filler or repeated schema content.

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 single-parameter, read-only metadata lookup, the description adequately explains what the tool returns and what problem it solves. It does not specify the exact response envelope or error behavior, but given the low complexity and existing annotations this gap is acceptable.

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 100% for the single name parameter, which already documents that it expects a table name like ZAPPSTEP_POS. The description adds essentially no additional parameter semantics beyond restating that the tool is about a table, so the baseline 3 applies.

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 identifies the resource as a table's foreign keys and enumerates the returned metadata: reference table, join fields, cardinality, and enforcement. It is distinguishable from siblings like tableFields and tableIndexes, though it lacks an explicit verb such as "lists" or "returns".

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 gives a clear use case: "The answer to 'where do the values of this field come from'", and adds "Reading only". It does not explicitly name alternatives or state when not to use the tool, but the intent and context are unambiguous.

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