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

No annotations exist, so the description must carry behavior alone, and it does more than most: page size of 50, server-side following of nextCursor up to max_pages (default 10 = 500), explicit truncated/cursor return contract for continuation, and redaction of provider internals in step copy. It omits auth/permission prerequisites and rate-limit behavior, which is the main remaining gap.

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 mode split is front-loaded in the first line and the 'Pass exactly one of' bullet structure maps one-to-one onto the parameter choice. Every clause carries operational information — pagination math, filter list, redaction note — with no restatement of the name or 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?

With no output schema and 12 parameters, the description does the heavy lifting: it enumerates returned fields, the aggregate campaign_ids list, truncation signaling, and continuation semantics. What is missing is minor — the remaining sequence object fields beyond the six named, and any note on permissions or error behavior.

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 baseline is 3; the description goes beyond it by explaining what workspace_id returns (campaignId, status, sendStatus, stopReason, tableId, rowId per sequence) versus what sequence_id returns (steps inline), and by tying status/channel/recipient/cursor/max_pages to list mode specifically. The _org/_group/_project/_instance/_run_id context parameters are not addressed, but they are documented in the schema.

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 opens with a precise definition of the resource ('one sequence = one enrolled person in a campaign') and then names the two distinct operations (list every sequence of a workspace, or fetch one sequence with steps inline). The scope statement — the list mode is 'the only view that sees all campaigns of a workspace at once' — lets an agent separate this from origami_campaigns and origami_rows 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?

It states the selection rule explicitly: 'Pass exactly one of' workspace_id or sequence_id, and describes what each yields, which is genuine when-to-use guidance. It also pre-empts a likely wrong turn by noting there is no global campaign list. It stops short of naming a sibling tool for campaign-level or row-level questions, so it is clear but not fully routing.

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