Workflows: step link

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

Annotations already declare a non-read-only, destructive write with no open-world access, so the description's remaining burden is to explain consequences. It does not say whether linking overwrites existing on-success/on-failure links, whether it can orphan steps, or whether it requires the workflow to be paused — the exact context a destructiveHint=true tool needs.

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?

A single compact sentence with the action and its parameters front-loaded and no wasted words. It is efficient, though arguably too terse given the mutation's destructive nature.

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?

With full schema coverage and annotations carrying the safety profile, the essentials are present and no output schema is needed. However, for a destructive linking operation the description omits whether existing links are replaced and what constraints apply to the target step IDs, leaving a real gap.

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 100%, so all four parameters (workflow_id, step_id, on_success, on_failure) are already documented in the schema. The parenthetical restates the two link parameters but adds no format, validation, or default details beyond structured data, so the baseline 3 applies.

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 names a specific verb ("Link") and resource ("workflow steps") and clarifies the operation as setting on-success/on-failure targets, which separates it reasonably well from siblings like workflows_step_update or workflows_step_add. It is clear on its own, though it does not explicitly contrast itself with the closest sibling (workflows_step_update).

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?

There is no when-to-use guidance, no mention of prerequisites (e.g. the referenced step IDs must already exist, or whether the workflow must be disabled), and no reference to the alternative workflows_step_update. The agent must infer usage entirely from the name and parenthetical.

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