close

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

With no annotations, the description bears full responsibility for behavioral disclosure. It adds a key behavioral trait: 'Never auto-pick save vs discard for dirty docs; surface the choice to the user.' This clarifies how the tool handles unsaved changes. However, it does not describe the full lifecycle (e.g., what happens after save/discard, whether the document can be reopened, or error conditions). It provides some transparency but not comprehensive.

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 description is two short sentences with no fluff. Each sentence earns its place: the first states the action, the second clarifies a critical behavioral constraint. It is front-loaded and immediately understandable.

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 simple tool with one parameter, the description covers the essential functionality (close active doc), parameter values, and a key safety behavior. It lacks details on edge cases (e.g., no open document) or side effects of specific confirm choices, but given the simplicity and absence of an output schema, it is reasonably complete.

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?

Since schema description coverage is 0%, the description must elaborate on parameters. It does so by specifying acceptable values ('save', 'discard', 'prompt') and the rule to never auto-pick, which gives meaning to 'confirm'. It doesn't explain each value's effect explicitly but implies it via the warning. This adds substantial value beyond the bare 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 clearly states the action: 'Close the active document.' It uses a specific verb (close) and a specific resource (active document), distinguishing it from sibling tools like save or open_doc, which serve different purposes. No ambiguity.

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?

The description provides guidance on the 'confirm' parameter values but does not explicitly discuss when to use this tool versus alternatives (e.g., when to save vs. close). It implies usage for closing, but lacks explicit exclusions or comparisons to other tools like save. The behavioral rule about not auto-picking save/discard is more about parameter handling than tool selection.

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