lean_run_code

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

Annotations declare readOnlyHint, idempotentHint, and openWorldHint, which already indicate safe, idempotent behavior. The description adds that the tool returns diagnostics, but does not elaborate on side effects (none expected), error handling, or output format. It adds marginal transparency beyond annotations.

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 sentences, each purposeful. First sentence states primary action and result; second sentence gives a critical requirement. No wasted words. Information is front-loaded.

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?

For a simple tool with one parameter and an output schema (not shown but exists), the description covers the essential purpose and constraint. It does not explain what 'diagnostics' entails or the environment context, but the output schema likely covers return details. The description is adequate for straightforward use.

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 coverage is 100% with one parameter described as 'Self-contained Lean code with imports'. The description reiterates the requirement to include all imports, reinforcing the schema's meaning. This adds clarity but does not introduce new semantic detail beyond the schema.

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 runs code and returns diagnostics. It uses 'Run a code snippet' as verb+resource, which is specific. However, it does not explicitly distinguish from sibling tools like lean_build or lean_verify, but the context of running a snippet rather than building a project is implied.

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?

No guidance on when to use this tool versus alternatives. It only states a requirement ('Must include all imports'), but does not mention implicit context, prerequisites, or when not to use. Sibling tools like lean_build or lean_verify are not compared.

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