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

Annotations already declare readOnly, idempotent, non-destructive, closed-world reads, so safety is covered. Beyond that, the description discloses the return composition (settings, messages, subsequent steps) and the fact that ids are the ones used in placeholders, which is behavioral context not present in annotations or schema.

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 short sentences, with the payload content front-loaded before the id-provenance note. No filler, though the phrasing "One step in full" is slightly clipped and could carry a clearer verb.

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 read-only single-resource getter with no output schema, the description covers what comes back and where ids originate. Missing only error behavior for a nonexistent step and any hint about the cost of pulling downstream steps.

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 50%: step_id is documented with an example, workflow_id is not. The description reinforces the step_id format (step_2, step_3) and adds provenance (from get_workflow) plus downstream use in placeholders, but says nothing about workflow_id.

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?

"One step in full" names the resource (a single workflow step) and enumerates what it returns: settings, messages, and following steps. That distinguishes it implicitly from get_workflow (the whole graph) and get_step_type (a type definition), though no sibling is named explicitly.

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 a real prerequisite: step ids come from get_workflow, so the agent knows it must resolve ids first. But there is no explicit statement of when to call this versus get_workflow, get_step_type, or edit_step, and no note about whether inspecting a step is needed before mutating it.

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