Cross-references

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

Annotations already declare the read-only, closed-world character, and the description's 'Everything' is consistent with openWorldHint=false, suggesting an exhaustive in-program search. It adds little beyond the annotations, so it neither harms nor meaningfully enriches the behavioral picture.

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 one-sentence description is short, with no filler. It is arguably too terse to carry much context, but for the core purpose it is 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?

For a two-parameter read-only lookup, the basics are present: target address and optional limit appear in the schema. But there is no output schema and no mention of what the returned references look like or how the limit applies, so an agent must infer behavior.

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?

Only the address parameter is documented in the schema; limit has no description, and the tool description adds no parameter-level meaning. At 50% coverage the description needed to compensate for the undocumented limit but did not.

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 phrase 'Everything that references an address' clearly names the returned resource (cross-references to a target address) and implies a lookup action. It is not a tautology, but it lacks an explicit verb and does not contrast itself with siblings like call_graph, which also deals with reference relationships.

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?

No guidance is given for when to prefer this tool over call_graph or other listing tools. The description merely states the function, so an agent gets no exclusions or selection criteria.

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