get_parm_references

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

With no annotations, the description must carry the behavioral burden. It discloses some edge-case behavior (e.g., 'unresolved' naming a removed target) and what the tool computes (pure ch() links and richer expressions). It does not explicitly state read-only semantics (though the 'get' prefix implies it) or address permissions, side effects, or rate limits.

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 well-structured: a one-sentence hook, then a compact explanation of incoming/outgoing, then a clear args list. The prose is dense but each sentence adds value, and the args section makes parameter semantics scannable. Slight verbosity in the node_dependents sentence could be trimmed, but overall it's efficient.

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 no output schema, the description should describe return values more concretely. It explains the conceptual content of incoming and outgoing references but never specifies the response structure, such as whether results are lists, maps, or contain metadata. The 'node_dependents' / 'node_references' terms are introduced but not fully defined, leaving gaps for an agent trying to understand the full result shape.

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%, so the description must compensate. It provides one-line explanations for each parameter: node_path is the node to inspect, parm_name narrows to one parameter, direction lists allowed values, and limit caps entries. These are helpful but quite terse; they don't clarify node_path format/requiredness beyond the schema and don't explain the behavior of defaults in context.

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 opening line 'Who references a parameter, and what it references — in one call' clearly identifies the tool's purpose. It further distinguishes between incoming and outgoing reference views, giving a specific verb-resource pairing. However, it doesn't explicitly differentiate from sibling tools, though none appear directly overlapping.

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 explains when to use each direction ('incoming' for what breaks if renamed, 'outgoing' for what the node reads) and the optional parm_name scope. It does not, however, give guidance about when to choose this tool over alternatives like link_parameters or get_parm_template_tree, and no when-not-to-use guidance is provided.

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