compare_runs

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

With no annotations, the description states read-only behavior, but lacks details on side effects, permissions, or data limits. This is adequate but not rich.

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?

One sentence plus 'Read-only' - extremely concise, front-loaded with verb 'Diff', 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?

Lists return values and read-only nature. Without an output schema, this helps. But lacks usage context (e.g., when to diff vs describe). Still fairly complete for a simple diff tool.

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 100% of parameters with descriptions already matching the tool's 'path to run_record or output dir'. The description adds minimal extra insight beyond grouping them as 'two RunRecords'.

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 diffs two RunRecords, listing specific return values (metric deltas, config changes, lineage relation, decision_facts). This distinguishes it from siblings like describe_run or 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 guidance on when to use this tool versus alternatives (e.g., describe_run for single runs, lineage_chain for lineage). The description only states 'Read-only' without excluding contexts.

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