create-run

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

Annotations already indicate write operation (readOnlyHint=false) and openWorldHint. Description adds minimal behavioral context beyond 'Create', not disclosing return value or 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?

Extremely concise (6 words) and front-loaded. However, could be slightly more informative without losing conciseness.

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?

Minimal description fails to explain key aspects like what a run is, return value, or prerequisites. For a write tool with 4 parameters and no output schema, more detail is needed.

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 all parameters documented. Description adds no extra meaning beyond what the schema already provides.

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?

Description clearly states verb 'Create', resource 'run', and context 'in an experiment'. It effectively distinguishes from sibling tools like 'update-run' and 'delete-run'.

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 explicit guidance on when to use this tool versus alternatives like 'update-run' or 'search-runs'. The description implies use for new runs but lacks contextual advice.

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