run_gauss_code

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

Since no annotations are provided, the description carries the full transparency burden. It discloses key behaviors: state persistence across calls, the requirement to use 'print' for output, compilation before execution (meaning undefined symbols prevent any execution), and the 'keep_state' parameter's effect. It also mentions error reporting (GAUSS's own error codes and source line). However, it doesn't describe potential side effects like file writes or resource consumption, though those are less critical for a code runner.

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 well-structured and appropriately sized for a tool with this complexity. It front-loads the primary purpose, then provides critical usage details (state persistence, printing requirements, compilation behavior), and ends with a parameter hint. Every sentence serves a purpose—no fluff or repetition. The use of bullet-like formatting via line breaks aids readability.

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?

Given the tool's complexity (full GAUSS language support) and the presence of an output schema, the description is remarkably complete. It covers execution semantics, state management, output expectations, error handling, and the key parameter. The context signals indicate an output schema exists, so the description correctly focuses on behavior rather than return structure. This matches the standard for excellent contextual completeness.

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?

With 0% schema description coverage, the description compensates by explaining both parameters: 'code' is implicitly the GAUSS code to run, and 'keep_state' is explicitly described as 'set false for a throwaway calculation that should leave the workspace untouched.' This adds meaning beyond the schema's bare type definitions, clarifying the purpose and typical usage of each parameter.

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's purpose: 'Run GAUSS code and return what it printed.' It explicitly identifies the main action (running GAUSS code) and the output behavior (returning printed output). It differentiates itself from siblings by being the core execution tool, while siblings handle state inspection, file I/O, and status queries.

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 provides strong usage context: it explains that symbols persist across calls (enabling step-by-step analysis), emphasizes using 'print' to display values, and notes the compile-before-run behavior. It doesn't explicitly contrast with sibling tools like 'clear_workspace' or 'run_gauss_code' specific alternatives, but the guidance is clear enough for an agent to know when to use this tool for code execution.

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