ghl_workflow_update_definition

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

The description is unusually transparent — full-overwrite deletion of absent steps, 422 on stale version, 409 on published workflows, 403 availability gate, rate-limit shape — but this directly conflicts with the annotation destructiveHint=false: a call that deletes every step omitted from the request IS a destructive update, and the description's stale-version rejection also undercuts idempotentHint=true (replaying the same body fails). The description is the more accurate source, but the agent receives contradictory signals from the two channels.

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 body is well front-loaded: limited availability, then the overwrite warning, then draft-only, then ordering. However the opening block drags in API-wide rate-limit budgets and log retention ('max range 30 days; retained 60 days') that have no bearing on invoking an update — wasted attention for the caller.

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 high-risk mutation with no output schema, the description covers prerequisites, failure modes, ordering and version safety thoroughly. The remaining gap is what a successful call returns (only the status code/path is named), which the caller may want in order to chain into a publish.

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; the description goes beyond it by explaining how `version` works (opaque, echo it back, stale value rejected before anything is written) and how the overwrite interacts with step IDs and in-flight contacts. It does not add anything about workflowId/locationId, which the schema already covers.

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 ('Replace a workflow definition in full') and immediately distinguishes itself from siblings by noting the draft-only requirement and pointing at Update Workflow Status / Validate Workflow Definition. An agent can distinguish it from create, get_definition and update_status without reading any schema.

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 an explicit ordered procedure (get step types -> build -> validate -> create -> publish), an explicit pre-condition sequence for this call (draft -> read -> update -> publish), and an explicit when-not-to-use case (published workflow returns 409). It even explains why the naive ordering fails.

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