diff_traces

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

With no annotations, the description carries the full burden. It discloses that both traces are fetched in parallel and that a summary of high-level field differences is returned. It also lists the exact fields compared. This is meaningful behavioral detail beyond simple 'compare'; it lacks only minor details like error handling or permissions.

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 compact and front-loaded. The first sentence states the core action, the second specifies behavior and output fields, and the final sentence adds use cases. Every sentence contributes; there is no fluff.

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?

The description covers the key aspects: action, parallel fetching, output summary with enumerated fields, and typical use cases. An output schema exists to handle return value details. The only minor gap is the 'project' parameter explanation, but the overall context is sufficient.

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 0%, so the description must compensate. The two required parameters (trace_id_a, trace_id_b) are self-explanatory given the tool's purpose, but the optional 'project' parameter is not explained in the description. This partial compensation earns a 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 opens with a specific verb+resource: 'Compare two traces side-by-side.' It clearly distinguishes itself from sibling tools like fetch_trace (single trace retrieval) and analyze_sessions by explicitly stating it compares two traces and lists the compared fields (name, user, latency, cost, etc.).

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?

It gives two concrete use cases ('why did trace X take longer than trace Y?' and 'what's different between these two runs?'), providing clear context for when to use the tool. It doesn't explicitly mention alternatives or exclusions, but the scenarios are specific enough to guide selection.

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