document

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

With no annotations, the description carries the full burden. It does disclose one real behavioral trait — that batch() runs the listed calls sequentially inside a single transaction — and the force/discard/overwrite parentheticals hint at consequence-bearing flags. It says nothing about handle lifetime, permission requirements, error behavior, or what happens to unsaved edits on close, which is a substantial gap for a heavily mutating tool.

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?

One dense line: purpose summary first, then an action-by-action signature list. Nothing is wasted, though the packed semicolon syntax is terse and could be hard to scan for a nine-parameter tool.

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?

Given nine parameters, nested call objects, no annotations, and no output schema, the description covers purpose and per-action arguments but omits the handle lifecycle that ties this tool to every sibling, plus any indication of what list()/info() return. Adequate as a routing label, incomplete as an operating manual.

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 only 44%, but the description compensates by mapping parameters to the specific action that accepts them (new(target_version), open(path), save(force), save_as(path, overwrite), close(discard), batch(calls), meta(set)), a relationship the flat schema does not express. Only the handle parameter is left entirely to 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 names concrete verbs (open, create, save, close, info) on the document resource and enumerates all ten actions of a multiplexer tool, so an agent knows this is the document-lifecycle entry point. It implicitly separates itself from sibling content tools (page, table, image, style), though it never states that relationship explicitly.

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?

Listing each action with its parameter signature implies when each applies (e.g. open pairs with path, save_as with path/overwrite), but there is no explicit ordering guidance such as 'open/new first to obtain a handle, then pass it to editing tools', and no when-not-to-use or alternative routing.

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