n8n_test_workflow

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

The annotations only flag non-read-only, open-world, and potentially destructive behavior; the description adds the auth prerequisite (N8N_MCP_ACCESS_TOKEN), the side effect of toggling the persistent 'Available in MCP' setting with explicit user confirmation, the read-only nature of prepare, and the failure mode where auto reports that it cannot be triggered. No contradiction with annotations — the per-method read-only qualifier is consistent with a whole-tool destructiveHint=true.

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 sentences carry the whole method model, the default behavior, and the auth prerequisite, front-loading 'Run a workflow' and method=auto. The middle sentence is dense with three methods packed into one clause, but for a 16-param, 5-method tool every clause earns its place and nothing is wasted.

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 tool this complex, the description plus a 100%-covered schema resolve almost every invocation decision: method selection, auth, prerequisites, and side-effect confirmation are all present. The notable gap is return-value semantics — with no output schema, the agent never learns what a run returns (execution ID? result data? error shape?), which matters when a workflow run starts a chained task.

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 every parameter already carries a precise semantic description, including pinData's wrapping rule, the timeout vs timeoutMs scoping, and executionMode's 'never chosen implicitly' caveat. The description adds the connecting glue — the method model and auth context — but the schema does the heavy lifting, so 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?

'Run a workflow' pairs a specific verb with a clear resource and is immediately differentiated from the 28 siblings (create/get/update/delete/list workflows). The method breakdown makes explicit that this tool executes, never manages, workflow definitions, and the trigger/HTTP vs MCP-server distinction removes ambiguity about what 'run' means here.

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 explicit routing logic: workflows with webhook/form/chat triggers use auto/trigger over HTTP, while triggerless workflows require prepare/pinned/direct through n8n's MCP server. It also states the fallback behavior (use exposeToMcp when n8n refuses) and the prepare-first requirement before pinned. It doesn't name exclusion conditions against sibling tools, but within the tool the when-to-use decision is unambiguous.

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