diff

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds the REFUSED outcome and mentions drill-in commands, but doesn't disclose more about side effects or error behavior. Given the annotations, 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?

The description is concise, with two sentences that front-load the purpose and then add details on output and behavior. It avoids fluff, though the first sentence is a fragment and the phrasing is somewhat jargon-heavy, preventing a perfect score.

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?

With five parameters, two required, and no output schema, the description should clarify the return format more thoroughly. It gives verdicts (MATCH, DIVERGED, REFUSED) and says it 'names the first event', but doesn't describe the event structure or the drill-in commands. The schema covers parameters, so this gap is in the output semantics, making it incomplete but not severely lacking.

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?

The schema provides 100% description coverage for all five parameters, so the schema already documents them. The description doesn't add extra meaning to parameters beyond referencing 'two runs' (run_a, run_b), so it remains at the baseline of 3.

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 states the tool finds the 'first causal divergence between two runs' and explains it aligns streams and names the first event. This is a specific function distinct from siblings like 'runs' or 'tree' which are not comparative. However, it doesn't explicitly contrast with alternatives, so it stops short of a 5.

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 implies the tool is for comparing two runs, but it doesn't explicitly state when to use it versus other tools or list exclusions. It mentions 'REFUSED when no verdict exists', hinting at a condition, but that's not enough to guide tool selection clearly.

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