List reference sites without symbol resolution for a project path, so you can trace where code entities are used before cleanup or refactoring.
Reference sites, resolution-free (the ce graph --sites rows).
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | subpath (default: project root) |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'resolution-free' as a trait but says nothing about read-only behavior, side effects, return format, pagination, or performance characteristics, leaving the agent with little operational context.
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 a single short sentence, so it is not verbose. However, the cryptic parenthetical CLI reference does not fully earn its place for an AI agent and leaves the core purpose unclear.
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?
There is no output schema and no annotations, so the description should explain what 'reference sites' means and what the tool returns. It fails to do so, offering only an internal shorthand that does not help an external agent invoke the tool correctly.
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 100%, with the only parameter ('path') already documented as a subpath defaulting to project root. The description adds no additional parameter meaning, so the baseline of 3 is appropriate when the schema does the heavy lifting.
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 gives only a noun phrase ('Reference sites') and an internal CLI reference ('the ce graph --sites rows'), without a clear verb or output description. It does not distinguish this tool from siblings like similar_units, clone, or structure, leaving the agent to guess what operation is performed.
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 alternatives. The phrase 'resolution-free' hints at a condition but does not explain when or why an agent should choose graph_sites over the many other code-analysis siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.