xrefs

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

Annotations declare readOnlyHint=false and idempotentHint=true, but the description says only 'Read', so it never explains the non-read-only character implied by the annotation and by the analysis_project_id parameter, which retains results in a project. It also omits whether an open binary/document context is required and what the returned reference set looks like. Not flagged as a contradiction because 'read' can describe the analysis operation while persistence happens in project state, but the description leaves the side effect undisclosed.

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 front-loaded sentence with zero filler, which is structurally clean. However, for a three-parameter tool with non-obvious address semantics, that brevity reads as under-specification rather than discipline.

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, so the description should describe the shape of the returned cross-references, and it does not. Combined with undocumented parameters and no statement of required context (open binary, document resolution), an agent cannot call this reliably without trial and error.

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 only 33%: only analysis_project_id is documented in-schema, while address and document carry no descriptions. The description adds nothing to clarify what address format is expected (module-relative vs absolute, as the regex allows both) or what document selects, so it fails to compensate for the coverage gap.

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 (read) and a specific resource (static references to and from an ELF address), which is precise within a reverse-engineering domain. It does not distinguish itself from nearby siblings such as procedure_references, procedure_callers, or trace_android_references, so an agent cannot tell from the text alone when xrefs is the right call.

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 when-to-use guidance, no prerequisites (does it require an open binary session?), and no mention of any alternative tool. The word 'static' hints at a distinction from dynamic tracing but never states it explicitly.

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