get_references

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

Discloses LSP dependency, returns every location in codebase, results include file path and line/column. Could mention potential latency for large codebases or requirement of active LSP server, but still transparent.

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?

Four sentences, concise and front-loaded. Every sentence adds value with no redundancy.

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?

Describes return format (file path and line/column) despite no output schema. Covers purpose and usage but lacks discussion of error cases or performance implications. Could be more complete given 6 parameters.

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 0%, description only covers the required parameters (file_path, line, column). Does not explain optional parameters like include_declaration or position_pattern, leaving them ambiguous.

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?

Clearly states the tool finds all references to a symbol at a specific location via LSP. Distinguishes from sibling tools like go_to_definition by focusing on 'references' and 'usage'.

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?

Provides explicit use cases: determine if symbol is dead, understand call sites before refactoring, trace data flow. Lacks explicit exclusions or alternatives like get_cross_repo_references.

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