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

Beyond the annotations (readOnly=false, idempotent=true, destructive=false), it discloses three behaviors the agent could not otherwise infer: cascade deletion of nested steps inside a condition/loop, a runtime refusal condition tied to downstream readers, and versioned persistence with an undo.version_id to restore. The undo detail also reconciles why destructiveHint is false despite a removal.

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 short sentences, each carrying distinct information: scope/cascade, refusal precondition, versioning/undo. The most decision-relevant facts come first with 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 two-parameter mutation with no output schema, the description covers cascade effects, failure conditions, and recoverability well. It leaves out how errors surface and what identifier the undo reference is tied to, but nothing essential to invoking it correctly is missing.

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% and both parameters are required, so the schema supplies names only. The description never explains workflow_id or step_id, nor what format an ID takes; it only refers abstractly to "its output." The description does not compensate for the coverage gap.

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?

Specific verb ("Remove") plus specific resource ("one step"), with a parenthetical clarifying that removing a condition or loop also removes its nested steps. That cascade note makes the tool unambiguous against siblings like edit_step or remove_knowledge_source, 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?

The description gives a concrete precondition that selects against use: the call is refused while another step reads the removed step's output. That is real when-not guidance rather than vague context, but it says nothing about choosing between remove_step and alternatives such as edit_step or archive_workflow.

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