invariance_eval_experiment_compare

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the description doesn't need to restate safety. It adds value by disclosing the output format (CompareResponse with per-case ScoreDelta entries and aggregate deltas), which goes beyond the annotations. No contradictions found.

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?

The description is a single, front-loaded sentence that states the action, output, and purpose with zero waste. It is concise and immediately informative.

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 the read-only nature (annotations) and fully documented parameters (schema), the description provides sufficient context for an agent to call it correctly. It mentions the output structure, though it doesn't cover edge cases like missing runs or error handling, which are not critical for a read-only comparison 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 description coverage is 100% and both parameters are well-documented: 'id' is the new/candidate run, 'baseline' is the baseline to diff against. The description adds no further parameter detail beyond what the schema already provides, so it stays at the baseline score.

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 verb 'compare', the resource 'two scored eval runs', and specifies the output structure (CompareResponse with per-case ScoreDelta and aggregate deltas). It distinguishes this from sibling tools like invariance_run_metrics or invariance_eval_run_results by focusing on case-by-case comparison against a baseline.

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?

The description gives an explicit use case: 'Use to surface regressions vs. a baseline.' This tells the agent when to invoke it. It doesn't explicitly contrast with alternatives, but the context of comparing runs vs. getting metrics is clear enough given the sibling names.

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