find_references

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

Discloses that it returns a token-capped file:line list with no bodies, resolves the declaration, and accepts symbol name or position for disambiguation. No annotations provided, so description carries full burden; it adequately covers key behaviors.

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?

Well-structured, front-loaded with key info. Each sentence adds value. No redundancy or fluff.

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?

Covers main usage, input options, and return format. Lacks mention of error cases (e.g., symbol not found) or limitations beyond token cap. Still fairly complete given no output schema.

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?

Adds meaning beyond schema for 'symbol' (just name, no position needed) and explains how path+line+character disambiguates overloads. Schema coverage is 63%; description enriches the main parameters but does not describe projectPath, backend, maxResults.

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 clearly specifies that the tool finds every call site/usage of a symbol using semantic analysis (language server), not text grep. It distinguishes itself from grepping and other tools like search_text. States it's the tool for modifying code.

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 says to use when modifying code and to prefer over grepping. Provides clear context but does not explicitly exclude cases where text search is needed (e.g., regex). Still strong guidance.

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