run_experiment

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

With no annotations, the description must disclose behavioral traits. It mentions safety, autonomy thresholds, and timeout bounding. But it lacks details on what 'safely' entails, timeout behavior, or potential side effects, limiting full transparency.

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-load key information: purpose, safety, mode autonomy, and timeout. No redundant words, every sentence adds value.

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 no output schema and 17 sibling tools, the description is minimal. It covers mode and approval but omits details like what 'run' means, how to monitor progress, or how results are accessed. Missing context for comprehensive agent decision-making.

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 0%, so the description must compensate. It explains mode values ('small=autonomous; gpu/medium/long need approval'), adding semantics. However, it does not describe 'approve' or 'experiment_id' meaning, leaving gaps in 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?

The description clearly states the tool's purpose: running an experiment safely, with mode-specific autonomy (small vs. gpu/medium/long). It distinguishes from sibling tools (e.g., create_experiment, get_experiment) by being about execution, not creation or retrieval.

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?

It provides context on when to use autonomously (small mode) vs. requiring approval (gpu/medium/long). However, it does not explicitly mention when not to use the tool or suggest alternatives, leaving some ambiguity for the AI agent.

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