Diagnose Run

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

readOnlyHint=true already tells the agent this is a safe, non-mutating operation, so the description isn't carrying the safety burden. It does add useful context beyond annotations: the exact diagnostic outputs returned and the agenticlens>=0.7.0 dependency requirement. It stops short of disclosing cost/latency of an investigation run or how baseline affects output.

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, front-loaded with the verb and resource, no filler. The output enumeration is dense and reads as a run-on list, but every element is informative rather than padding.

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?

For a 6-parameter tool with nested objects and no output schema, the description does the right thing by spelling out the return contents. However, the three opaque object parameters and the passed-in run structure are left entirely unexplained, so an agent cannot construct a valid call without opening the schema.

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 only 17% – only session_id is documented – and the description compensates weakly. It implies baseline ("optional baseline runs") and include_narrative ("investigation narrative"), but leaves run, budget, and config as untyped-in-practice objects with no explanation of their structure or purpose, which an agent cannot infer.

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?

"Diagnose a trace run" is a specific verb+resource, and the enumeration of outputs (failure taxonomy, faulty step/agent with confidence and spans, incident timeline, anomalies, narrative) makes the tool's job unambiguous. It does not, however, explicitly differentiate itself from close siblings like lens.compare_runs, lens.analyze_workflow, or lens.score_analysis, which overlap in scope.

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 states what the tool produces but gives no when-to-use or when-not-to-use guidance, no prerequisites, and no pointer to alternative lens.* diagnostic tools. The only conditional hint is "anomalies against optional baseline runs," which describes a feature rather than selection criteria.

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