Workflows: step link

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

Annotations already declare destructiveHint=true, so the safety warning partly overlaps structured data. The description adds real value beyond them: omitted links retain their current value (partial-update semantics), links can be changed but not cleared, and name/action/params are preserved. It does not describe the response, though no output schema exists.

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?

Four sentences, front-loaded with the core action before the behavioral caveats. Each sentence carries information (what it does, params semantics, constraints, safety caution), though it is slightly longer than strictly necessary.

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 destructive mutation with no output schema, the description covers the important ground: what changes, what is preserved, what cannot be done (clearing), and the confirmation requirement. The only gap is the absence of any note on the result or effect verification.

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 100%, so the baseline is 3 and the schema documents all four parameters. The description adds the provenance of the step ids (from workflows_get) and clarifies that omitting a link is a no-op rather than a reset, which is meaning beyond the schema's terse 'Step ID to execute on success'.

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?

States a specific verb and resource (link workflow steps) and immediately names the two fields it governs, on_success and on_failure. This distinguishes it from siblings like workflows_step_update (name/action/params) and workflows_step_add, which the description explicitly carves out by noting those properties are untouched.

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?

Gives clear context for use (set next-step routing by step id) and a caution to confirm with the user before running. It also flags a limitation — links cannot be cleared here — which implies when a different tool is needed, but it never names that alternative sibling explicitly.

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