compare_runs

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

Declares 'Read-only', which is a key behavioral trait. Lists return values (metric deltas, config changes, etc.) to set expectations. No annotations to contradict.

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: first defines core function, second lists outputs and safety. No wasted words.

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?

No output schema, but description explicitly lists return types. Only two simple parameters with clear schema descriptions. Complete for its complexity.

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 parameters fully (100% coverage). Description adds minimal extra meaning beyond reinforcing that parameters are paths to run records or output dirs.

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 it diffs two RunRecords or output dirs, with specific outputs listed. It is distinct from siblings like 'describe_run' and 'lineage_chain'.

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 vs alternatives. The name implies comparison, but no when-not or alternative directions are given.

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