page

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

No annotations are provided, so the description carries the full behavioral burden and does not meet it. It never states that every action mutates the document, that a valid handle is required (the schema's handle description hints at this but the description does not), what happens to existing settings when an action is re-applied, or how header/footer op=remove behaves.

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?

A single dense but front-loaded block: the topic comes first, then the action signatures. Given 10 actions and 40 parameters, this is a compact representation with essentially no filler sentences. It could be more scannable if the action list were broken out line by line, but 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 high-complexity dispatcher (10 actions, 40 params, nested objects, no output schema, no annotations), the description provides only the action-to-parameter map. It omits return/effect information, error conditions, whether actions are idempotent, and the handle lifecycle. An agent could pick an action but not reliably predict the outcome.

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 35% across 40 parameters, so the description should compensate more than it does. Its real contribution is the per-action parameter grouping, which the flat schema with additionalProperties=false cannot express — the agent learns that page_number takes side_char but columns takes separator. However, several parameters (items, fill, widths, hide_first, side_char) remain undocumented in both schema and description, and no enum value meanings are added.

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 leading clause names the resource domain concretely (paper, margins, columns, page numbers, headers/footers, breaks, borders, master page), and the action list enumerates the concrete operations. An agent can tell this is the page/section-layout tool rather than char_format or para_format. It stops short of explicitly contrasting itself with siblings such as style or section-adjacent 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?

There is no statement of when to use this tool versus alternatives, no prerequisites, and no exclusions. The action names imply use cases (setup, header, footer, break), but the agent is left to infer which action to pick and when a page-level tool is preferable to a paragraph- or section-level sibling.

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