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

Annotations only say readOnlyHint=false, openWorldHint=false, idempotentHint=false, destructiveHint=false. The description adds critical behavioral context: it calls model providers and costs money, it is priced and refused against budget before starting, it does not re-execute external connector steps (served from baseline recordings), and agent steps are limited to offline calculation tools. It also clarifies the return value is the new run, not a comparison. This goes well beyond the annotations.

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 core action is in the first sentence, followed by cost/safety warnings, then behavioral constraints, then return value and permissions. Every sentence adds distinct value with no redundancy.

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 action, cost implications, side-effect behavior, return value, and required permissions. It lacks explicit parameter definitions and does not describe error cases or what happens if the budget is refused, but given the tool's complexity and the absence of an output schema, the description is quite complete for an agent to invoke it correctly. A small gap remains around the exact meaning of set_id and baseline_session_id.

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 carries the burden for parameter meaning. The description mentions 'baseline' and 'new run' but does not explicitly explain set_id or baseline_session_id. However, the parameter names are fairly self-explanatory (set_id = comparison set ID, baseline_session_id = baseline workflow session ID), and the description's context about baseline responses helps infer their roles. Still, explicit parameter-level detail is missing, so a 3 is appropriate.

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 action ('Re-run a member's workflow as it stands today and record the result as a new run'), the resource (workflow run), and the key distinction from a comparison ('Returns the new run, not a comparison of it'). It also differentiates from siblings like run_workflow and compare_scope_baseline by specifying the baseline and the no-external-side-effects behavior.

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 explicitly states when to use this tool: to re-run a workflow against a baseline and record a new run. It also gives exclusions: it does not act on the outside world a second time, connector steps are served from baseline responses, and agent steps keep only offline calculation tools. This clearly distinguishes it from run_workflow and compare_scope_baseline, and it names required permissions (comparisons:write and workflows:run).

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