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

With annotations only declaring readOnlyHint=false and destructiveHint=false, the description carries real behavioral weight: at most one open run per workflow, re-delivery semantics when no edgeId is supplied, and that later calls return only instruction titles after first delivery. These stateful/side-effect traits are not derivable from 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?

Three sentences, front-loaded with the core action before the disambiguation and branch/delivery caveats. Dense and slightly clause-heavy, but no sentence is filler.

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?

No output schema exists, and the description partly covers return shape — full step re-send versus instruction titles only. For a 4-param stateful tool with annotations only covering safety, this is largely sufficient, though auth/permission prerequisites go unstated.

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 coverage is 100%, so the baseline is 3, but the description adds genuine meaning: edgeId selects a configured branch (including one that names bypassed optional stages), and runId/workflowId are framed as alternative disambiguators for open runs.

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 first sentence gives a specific verb pair and resource: 'Reconcile and read an open workflow run, then deliver its current step.' That is enough to separate it from get_workflow (pure read) and start_workflow (new run), though it never names those siblings directly.

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 concrete selection rules — 'name it with runId or workflowId when several are open' and 'Pass an available edgeId before reporting to choose a configured branch' — plus the no-edgeId fallback. It stops short of naming an alternative tool for when resume is the wrong choice.

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