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

Annotations provide readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=true. The description adds useful context: 'Steps run on YOUR configured provider keys' (explaining authentication and cost model), 'If a step is a human checkpoint, returns the session id to advance' (checkpoint behavior), and 'Requires authentication' (reinforcing auth needs). It does not mention rate limits, error handling, or cost implications beyond the key usage, but the existing annotations already cover the core safety profile.

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 five sentences long, starting with the primary action. It is efficient and front-loads the key information. It could be slightly more structured (e.g., bullet points for the checkpoint and polling guidance), but it remains clear and concise.

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?

Given the tool has an output schema (not shown but present) and the description covers the main workflow behavior, polling pattern, checkpoint handling, and authentication, it is fairly complete. It does not discuss error scenarios or what happens if the workflow slug is invalid, but the existence of sibling tools like 'list_workflows' mitigates this. The description sufficiently equips an agent to use the tool correctly.

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?

The input schema has 100% description coverage, so the schema already documents all five parameters. The description adds minimal parameter-specific value: it mentions the default return behavior (related to wait_seconds) and the provider key usage (context for the workflow parameter). For a fully covered schema, a baseline of 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 starts with 'Start a multi-step workflow pipeline and return its session id immediately by default,' which is a specific verb+resource combination. It clearly distinguishes from siblings like 'advance_workflow' (for checkpoints) and 'get_workflow_session' (for polling individual steps).

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 says to 'Poll get_workflow_session for each step's model/provider and output' and explains checkpoint handling ('If a step is a human checkpoint, returns the session id to advance'). It implies when to use the tool versus polling, but it does not explicitly mention when not to use it (e.g., alternative tools like 'test_workflow_step' or 'plan_workflow').

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