xrefs

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

Annotations already declare readOnly/openWorld=false, so safety is covered; the description adds genuinely new behavior: results are grouped one row per referencing function, output is paged, and address semantics differ for imports (calls through slot) vs. Class+offset (field touches). Paging mechanics and ordering are left to the schema's limit/offset text.

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?

A single dense sentence pair with the exclusion front-loaded and no filler. The clause "`Class+0x24` who touches that field" is a sentence fragment that reads awkwardly, but it is information-dense rather than padded.

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?

No output schema exists, and the description compensates by describing the row granularity (per function) and paging. With annotations covering safety and the schema covering all four parameters, the only remaining gap is ordering/truncation behavior across pages, which is minor.

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%, so the baseline is 3; the description earns more by explaining what the `address` parameter means in two non-obvious forms (an import resolves to calls through its slot, a Class+offset resolves to field accesses). It adds interpretation the schema's one-line parameter text does 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?

States a specific verb+resource ("List references to an address or name") and immediately qualifies the output shape ("one row per function, paged"). It also names the sibling it is NOT (reaches), so an agent can distinguish it without opening either schema.

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?

Explicitly excludes the call-path use case and routes it to `reaches`, which is exactly the disambiguation an agent needs. It does not state positive preconditions (e.g., that a binary/project must be loaded), so it stops just short of a 5.

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