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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely new behavioral context: `next_step` should be followed blindly, `pending_confirmations` holds the `APPROVE_MAPPING` confirmation, options must never be invented, and relayed fields are fenced as `<relayed …>` with instructions inside them ignored. The prompt-injection handling and the 'no second approval' rule are exactly the kind of behavior the annotations cannot convey.

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?

Purpose is front-loaded and the agent-facing sequence (read, follow `next_step`, confirm, map, submit) is ordered sensibly. It is dense but nearly every sentence carries an instruction; the only soft spot is some repetition around the relayed-text caution, which gets two separate mentions.

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?

An output schema exists, so return values need not be re-explained, and the description still adds the important shape of the response (`pending_confirmations`, `next_step`, approved state). The main gap is the unfiltered/`item_id`-filtered distinction, which an agent would need in order to call it correctly.

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 25% — only `include_editor` is documented (in the schema, not the description). The description mentions `order_id` and `session_id` only in passing and never explains `item_id`, which presumably narrows the status to a single item, nor that `include_editor` is large and optional. With that much undocumented surface, the description should have compensated and does not.

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 opening line states a specific resource and scope: each item of a given `order_id` and where it stands in print-file page mapping. It names sibling tools (`prepress_confirm`, `prepress_map_pages`, `prepress_submit_mapping`) in a supporting role, so an agent can see this is the read/state-inspection entry point. The phrasing 'Where each item ... stands' is slightly oblique but unambiguous in context.

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?

Explicitly says to read it before and after every other prepress tool and that it is how you find the open approval. It further routes the agent: send the chosen option via `prepress_confirm`, place pages via `prepress_map_pages` with `positions`, and call `prepress_submit_mapping` without re-asking once the item is `approved`. That covers when to use this tool and when to hand off to each alternative.

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