repo.references

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

Without annotations, the description carries the full burden; it reveals the analysis strategy (AST/lexical) and return fields (file paths, line numbers, etc.), enough for an agent to understand the tool's read-only nature, though it doesn't explicitly state idempotency or lack of side effects.

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 two-sentence summary that front-loads the core purpose and then details the return output, with no redundant or irrelevant information.

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?

Despite no output schema, the description explicitly states what is returned (file paths, line numbers, strategy, confidence), covering key aspects for a reference-finding tool; it could mention behavior when symbol is not found but is otherwise adequate.

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%, and the tool description does not add significant meaning beyond the parameter descriptions already provided in the schema (e.g., 'Optional file path to scope', 'Maximum number', 'Symbol name').

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 states the tool finds cross-file references to a named symbol, uses AST or lexical analysis, and returns specific information, effectively distinguishing it from sibling tools like repo.search.

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?

The description implies usage for finding references but does not explicitly contrast with similar tools like repo.search or repo.outline, nor provide when-not-to-use guidance.

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