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

Annotations only declare the non-read-only, non-destructive, closed-world profile; the description adds real behavioral context beyond that: the document is persisted, a summary message lands in the Deckly chat, and the whole change is undoable by the person, which explains why destructiveHint is false. It still omits failure modes (e.g., what happens if the document id is invalid or not currently open).

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 front-loaded sentence leading with the core action, then the side effects in order. The parenthetical about undo is a little tangled but every clause carries information; nothing is padding.

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 two-parameter, no-output-schema mutation tool with annotations already covering the safety profile, the description covers the outcome, the side effect, and reversibility. The remaining gaps — preconditions (document must be open) and error behavior — are modest but real.

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 0%, so the description carries the burden; it partially compensates by explaining that 'summary' becomes a chat message in Deckly that the person can undo. It says nothing about document_id (presumably the currently opened document) or any format/length expectations for the summary.

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 states a specific verb and resource ('Close the work on a document') and spells out the concrete effects: the document is saved, a summary is written to its chat, and editing is reopened for others. That clearly separates it from siblings like export_document or share_document, though it never explicitly names the counterpart open_work, which the agent must infer.

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?

Usage is only implied — the agent can deduce it should call this when work on a document is complete, since it releases the document for others to edit. There is no explicit when-to-use statement, no exclusion against export_document/share_document, and no note on whether the document must first be opened via open_work.

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