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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so no restatement is needed. The description adds useful non-obvious behavior: conditional delegation to get_relation_graph with O(1) performance when the relation index is loaded, plus a warning against redundant calls. It does not detail the exact result record shape, but for a read-only lookup this is acceptable.

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?

Three sentences each earn their place: one defines results, one defines call timing, and one defines the relationship to a sibling tool. There is no filler, repetition, or vague framing.

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 lookup, the description is complete enough: it states what is returned, when to call it, and how to avoid duplicating work with get_relation_graph. No output schema exists, but the return contents are summarized at an adequate level for an agent to invoke the tool correctly.

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 input schema has 100% description coverage for objectName, including examples, so the baseline is 3. The description clarifies what the tool does with the object name but adds no new constraints, formatting, or semantic details for the parameter itself.

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 names a specific operation—returns ALL FK/DeleteAction/DataSource relations—and explicitly covers both outgoing relations and incoming back-references. It is clearly distinguishable from related tools such as get_relation_graph by describing both the scope and direction of results.

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 gives an explicit trigger: 'Call BEFORE generating multi-object code' to understand the dependency graph. It also names get_relation_graph as an internal delegation target and warns 'do NOT call both tools for the same object', which prevents duplicate work.

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