workflow_run

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

With no annotations present, the description carries the full burden. It discloses per-step logging, the failure index behavior, and that start_at skips already-succeeded steps. It does not explain stop_on_error semantics or the side-effect profile of executing arbitrary tools, but it gives substantially more than a bare summary.

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 tightly packed sentences deliver the core action, resumption behavior, and a concrete step format. The inline JSON example is efficient and earns its place; there is no 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?

For a complex orchestration tool with no output schema and no annotations, it covers the step shape, logging, and resume flow well. Remaining gaps are the exact per-step log return format and the behavior of stop_on_error when false, which an agent would need when handling failures.

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 67%. The description adds real value by giving a concrete step example with tool, args, and label marked optional, and by re-explaining start_at as resume-after-success semantics. The stop_on_error parameter lacks explanation, but its default true and the failure-index behavior make it less critical.

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?

Description opens with a specific verb phrase, 'Run a list of tool calls in sequence', and identifies the exact resource, 'any tool this server exposes'. It also differentiates from the many single-action siblings by describing orchestrated execution and per-step logging, with a concrete step example.

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 clearly conveys when to use the tool: when multiple tool calls must be executed in order. It adds resuability as a concrete reason to choose it. It does not explicitly name alternatives or include when-not-to-use conditions, but the context is strong 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.