realpath

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

Explicitly states read-only, no side effects, aligning with readOnlyHint annotation. Adds error behavior (fails if target doesn't exist) and return format (JSON). No contradiction.

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?

Two concise sentences front-loading purpose, then usage guidance and alternatives. 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?

Complete for a path resolution tool: covers behavior, error handling, return format, and sibling distinction. Input schema is comprehensive; description fills in missing context.

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 covers all parameters (100% coverage). Description adds value by explaining strict parameter's effect on existence check and mentioning JSON return, enhancing parameter understanding.

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 it resolves file paths to absolute canonical form, following symlinks. Distinguishes from sibling 'readlink' by specifying that readlink is for reading symlink targets without full resolution.

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 context: use to normalize paths for comparison or before file operations, and explicitly states when not to use (reading symlink targets) with alternative 'readlink'.

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