function.var_refs

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

No annotations are provided, so the description carries the full burden. The description does not disclose behavioral traits such as whether results include cross-references to other functions, whether the tool depends on prior analysis (e.g., MLIL/HLIL must be generated), or if there are side effects (e.g., triggering analysis). It only states the basic action, leaving significant gaps.

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 extremely concise, using a single sentence with no filler. It is appropriately front-loaded with the core action. However, it may be too brief given the complexity of the tool and the number of required parameters, sacrificing detail for brevity.

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 that there are 4 parameters (3 required), no output schema, no annotations, and a complex domain (variable references in IL analysis), the description is insufficiently complete. It does not explain the relationship between variables and functions, the meaning of results (e.g., addresses vs. IL indices), or any constraints. A more complete description would cover these aspects.

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?

With schema description coverage at 0%, the description must compensate, but it adds no parameter-specific information. The parameters 'session_id,' 'function_start,' 'variable_name,' and 'level' are not explained or contextualized beyond the schema. For example, 'level' restricts to MLIL/HLIL but the description offers no insight into how the choice affects output. Baseline would be 3 if coverage were adequate; here, the gap lowers the 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 states 'List variable references in MLIL/HLIL,' which clearly specifies the verb (list), resource (variable references), and scope (MLIL/HLIL). However, it does not differentiate from the sibling tool 'function.var_refs_from,' which is likely similar (listing references from a variable). The minimal description is clear but lacks distinction.

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?

There is no guidance on when to use this tool versus its siblings, particularly 'function.var_refs_from' or other reference-listing tools like 'xref.code_refs_to.' The description does not mention prerequisites, such as needing a specific function analysis mode (MLIL or HLIL already active), nor does it advise on alternatives. The agent must infer usage solely from the name and description.

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