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

With no annotations, the description carries the full load and does so: plan-tier and confirm prerequisites, per-actionType behavior ('send_message' sends verbatim with template tokens, 'ai_message' drafts in the coach's voice and is held for approval unless requireApproval is false, 'notify_coach' only reminds the coach), and concrete safety limits (8am–9pm client-local, max 2 messages per client per day, each event fires once). That is exactly the kind of side-effect and rate-limit detail an agent cannot get from the 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?

The branching structure and safety limits are front-loaded and every clause carries information relevant to correct invocation. It is dense as a single block, and the clause ordering (mode choice, then action semantics, then limits) could be signposted, but there is 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 9-parameter mutation tool with no annotations and no output schema, this is close to complete: prerequisites, mode selection, action semantics, and rate limits are all covered. The remaining gaps are the undocumented `via` channel and the unspecified valid `triggerType` values, which an agent would still have to guess.

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 only 11% (just `confirm`), so the description must compensate, and it does explain templateKey, name, triggerType, days, actionType, text, and requireApproval semantics. However, the `via` parameter (chat/push/email) is never mentioned, and `triggerType` is a free-form string with no allowed values given, leaving two of nine parameters ambiguous.

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+resource ("Create a workflow") and immediately distinguishes the two creation modes: template-based via `templateKey` or fully specified via `name`/`triggerType`/`actionType`/`text`. It names the sibling that supplies template keys (list_workflow_templates), so an agent can tell this apart from list_workflows and the other workflow tools.

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 clear routing between the template path and the custom path, plus the eligibility gate (confirm-gated; Coach Pro or gym plan required) and the direction to obtain keys from list_workflow_templates. It stops short of naming when-not-to-use, e.g. that approval/review flows belong to review_workflow_draft or list_workflow_approvals rather than create_workflow.

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